School agent Jobs

????Recruitment Network is Hiring: Travel Agent <br>???? Requirements: <br>-Strong and proven experience in travel packages. <br>???? Location: Beirut, Lebanon <br>???? To Apply: <br>Please send your CV to: wakedmarc8@gmail.com

<h2 class="h5">Job description</h2> <div class="t-break" data-jb-field="description"> <span>Aspire Software is looking for an AI Engineer to join our team in Lebanon.<br> Here is a little window into our company: Aspire Software operates and manages wholly owned software companies, providing mission-critical solutions across multiple verticals.<br> By implementing industry best practices, Aspire delivers a time sensitive integration process, and the operation of a decentralized model has allowed it to become a hub for creating rapid growth by reinvesting in its portfolio.<br> About the job: This is a builder role for someone obsessed with what agents can actually do in production.<br> You'll design and ship autonomous AI systems that operate inside the Polygon marketplace — agents that understand jewelry listings, assist buyers and sellers, surface intelligence across decades of trade data, and automate workflows that have been manual for forty years.<br> You won't just be wiring up LLM calls.<br> You'll be designing agentic systems end-to-end: tool definitions, planning loops, memory, evals, guardrails, observability, and the product surfaces that put these capabilities in front of real users.<br> Key Responsibilities Design and build agentic systems that power core marketplace experiences — listing intelligence, semantic and multi-step search, buyer/seller assistants, trade matching, content moderation, and market analytics Architect tool-using agents with reliable planning, execution, and recovery Build the supporting infrastructure: RAG pipelines, vector search, evals, prompt management, traceability, and cost/latency monitoring Partner with product and design to translate agentic capabilities into UX that members actually use and trust Establish patterns and primitives so the rest of the engineering team can ship agent-powered features confidently Stay on the frontier — evaluate new models, frameworks, and techniques and bring the ones that matter into production 3 - 5 years of experience Production experience building agentic systems with LLMs — not just chat wrappers, but agents that plan, use tools, and complete multi-step tasks Deep familiarity with at least one major LLM API (Anthropic, OpenAI, or equivalent), including tool use / function calling, structured outputs, and streaming Experience designing and running evals for non-deterministic systems Strong software engineering fundamentals — TypeScript/Python, modern web stack, API design Pragmatic judgment about when to use agents, when to use simpler pipelines, and when not to use AI at all</span> </div>

The Merchandiser is responsible for ensuring that products are presented in an appealing way, maximizing sales potential in retail environments. This role involves planning and executing product displays, maintaining inventory levels, and working closely with sales teams to enhance the customer shopping experience. <br>Key Responsibilities: <br>o Create and maintain visually appealing product displays in stores to attract customers and increase sales. <br>o Implement planograms and merchandising guidelines provided by the company. <br>o Ensure that all products are well-organized, clean, and properly labeled with pricing and promotional information. <br>o Monitor stock levels and ensure that products are adequately stocked on shelves. <br>o Work with the supply chain or warehouse teams to manage product replenishment and prevent stockouts or overstock situations. <br>o Conduct regular inventory checks to identify slow-moving or out-of-stock items and take corrective actions. <br>o Adjust merchandising strategies based on sales performance and customer feedback. <br>o Prepare reports on merchandising activities and inventory levels. <br>o Communicate effectively with store staff to ensure merchandising plans are understood and implemented correctly. <br>o Conduct store visits and market research to gather insights on merchandising practices and customer behavior. <br>o Provide feedback to management on potential improvements to product assortment and merchandising strategies. <br>o Ensure that product displays contribute to a positive shopping experience for customers. <br>o Respond to customer inquiries about product location, features, or promotions. <br>o Work to create a shopping environment that reflects the brand’s identity and meets customer expectations. <br>o Ensure that all merchandising activities comply with company policies and brand standards. <br>o Maintain a clean and organized work area, including stockrooms and display areas. <br>o Adhere to safety regulations and store policies during merchandising activities. <br> <br>Needed Skills; <br>• Strong attention to detail and creativity in product display. <br>• Excellent organizational and time-management skills. <br>• Proficiency in using merchandising software, inventory management systems, and Microsoft Office Suite. <br>• Experience in retail, merchandising, or a related field. (not a must) <br>• High school diploma or equivalent

1. Company Description <br>Twellium Industrial Company Limited entered the Ghanaian beverage market in 2013, starting with products such as Rush Energy Drink and Verna Mineral Water. The company has since expanded to produce over sixty different beverage brands and flavors, including malt-based drinks and carbonated soft drinks, all made in Ghana and designed to be affordable. Twellium also produces McBerry biscuits and cakes, featuring a diverse range of products prepared under strict health and safety measures. The company is renowned for its commitment to quality and excellence, with a strong lineup of market-leading brands enjoyed by consumers across the region. <br> <br>2. Job Purpose <br>The Data Entry Clerk captures, validates, and maintains accurate production records for Twellium’s Kumasi facility. You will ensure that all batch logs, yield data, equipment readings, and quality checks are entered into the ERP/MES in a timely manner, supporting production planning, traceability, and continuous improvement efforts. <br> <br>3. Key Accountabilities <br> <br>Accurate Data Capture <br>Enter batch production data into ERP/MES immediately after runs <br>Record equipment parameters and manual adjustments <br>Log quality check results and deviations <br> <br>Data Validation & Reconciliation <br>Review entries for completeness against source logs <br>Correct discrepancies with Production Leads <br>Reconcile shift handover reports to prevent data gaps <br> <br>Report Generation & Distribution <br>Generate daily and weekly production summary reports <br>Distribute metrics to Production, Quality, and Maintenance <br>Archive reports and backup data per policy <br> <br>Continuous Improvement Support <br>Provide historical data trends for root cause analysis <br>Suggest enhancements to data capture workflows <br>Participate in 5S audits of documentation practices <br> <br>Compliance & Confidentiality <br>Maintain accurate timestamps and operator IDs <br>Adhere to GMP, ISO 22000, and data security protocols <br>Support audits with data extracts and logs <br> <br>4. Qualifications, Experience & Skills <br>Secondary school completion; diploma in Business or IT preferred <br>1–2 years in data-entry or administrative roles in manufacturing <br>Proficiency with ERP/MES systems and MS Office <br>Typing speed ≥ 50 WPM with high accuracy <br>Strong attention to detail and organizational skills <br>Good communication and ability to meet deadlines

<p>EVO Wallet is seeking an experienced Agents Supervisor to oversee agent network operations, ensure smooth branch activities, monitor transactions, and maintain compliance with operational and regulatory requirements.</p><p><strong>Desired Candidate Profile</strong></p><p>Bachelor's degree in Business Administration, Finance, Banking, Accounting, or related field.<br>3 5 years of experience in branch operations, banking, fintech, digital payments, retail operations, or agent network management.<br>Previous supervisory experience is preferred.<br>Strong knowledge of cash handling, reconciliation, branch operations, and payment systems.<br>Knowledge of AML/CFT requirements and compliance standards.<br>Strong leadership, communication, and problem-solving skills.<br>Ability to travel between branches and supervise multiple locations.</p>

<h2 class="h5">Job description</h2> <div class="t-break" data-jb-field="description"> <p>EVO Wallet is seeking an experienced Agents Supervisor to oversee agent network operations, ensure smooth branch activities, monitor transactions, and maintain compliance with operational and regulatory requirements.</p> </div><h2 class="h5">Skills</h2> <div data-jb-field="skills"><p>Bachelor's degree in Business Administration, Finance, Banking, Accounting, or related field.</p><p>3–5 years of experience in branch operations, banking, fintech, digital payments, retail operations, or agent network management.</p><p>Previous supervisory experience is preferred.</p><p>Strong knowledge of cash handling, reconciliation, branch operations, and payment systems.</p><p>Knowledge of AML/CFT requirements and compliance standards.</p><p>Strong leadership, communication, and problem-solving skills.</p><p>Ability to travel between branches and supervise multiple locations.</p></div>

<h2 class="h5">Job description</h2> <div class="t-break" data-jb-field="description"> Job Description<br><p><strong>About the Role</strong></p><br><p>We're looking for an AI Engineer to design, build, and scale the systems that power our AI-driven product. You'll work at the intersection of large language models, multi-agent systems, and production software, turning cutting-edge AI capabilities into reliable, user-facing experiences.</p><br><p><strong>What You'll Do</strong></p><br><ul><li>Design and implement LLM-powered pipelines, including prompt engineering, context management, and response synthesis</li><li>Build and optimize multi-agent orchestration systems where AI components interact, reason, and produce coherent outputs</li><li>Develop and maintain integrations with foundation model APIs (Anthropic, OpenAI, and others), managing latency, cost, and reliability at scale</li><li>Implement retrieval-augmented generation (RAG) and memory systems for persistent, context-aware behavior</li><li>Partner with the Evaluation/QA Engineer to build frameworks that measure output quality, coherence, and factual grounding</li><li>Collaborate with product and design to translate workflows into robust technical experiences</li><li>Ship production features across the stack, from the model layer to the application</li></ul><p>Monitor, debug, and improve system performance, token efficiency, and guardrails</p><br><br>Qualifications<br><ul><li>3+ years of software engineering experience, with hands-on work building LLM-powered applications</li><li>Strong proficiency in Python and/or TypeScript/JavaScript</li><li>Experience with LLM APIs, prompt engineering, and agentic frameworks (e.g., LangChain, LlamaIndex, or custom orchestration)</li><li>Familiarity with vector databases and RAG architectures (Pinecone, Weaviate, pgvector, etc.)</li><li>Understanding of multi-agent systems, tool use, and function calling</li><li>Experience designing evaluation and testing strategies for non-deterministic AI outputs</li><li>Solid grasp of API design, async processing, and scalable backend architecture</li><li>Comfort working in a fast-moving, ambiguous, early-stage environment</li></ul><br>Additional Information<br><ul><li>Experience with real-time streaming (WebSockets, SSE) for conversational interfaces</li><li>Background in fine-tuning, model distillation, or inference optimization</li><li>Familiarity with cloud infrastructure (AWS/GCP/Azure) and CI/CD</li><li>Contributions to open-source AI projects</li></ul><br><br> </div>

Position Summary: <br> <br>Responsible for delivering high customer service quality to OMT customers and agents, analysing their needs and keeping them abreast of OMT services. Accountable for ensuring high customer satisfaction by providing prompt, efficient and courteous service to OMT customers & agents through solving their cases, answering their queries, participating in surveys and reporting problems to concerned departments. <br> <br> <br> <br>Primary Duties and Responsibilities: <br> <br>Agent & Customer Relationship Management: <br> <br>Handles incoming calls from customers with high professionalism by resolving their problems, answering their questions or providing them with information following Contact Center procedures <br>Analyses and evaluates agents/ customers’ requests; gathers needed data and case details and reports or escalates case to the concerned department by email when needed <br>Follows up on agents/ customers’ cases and provides them back with updates on their case when needed <br>Maintains accurate records and profiles for all agents/ customers and their cases whether seeking for information or submitting a complaint; updates system continuously along with case status <br>Updates and maintains database and ensures data integrity and accuracy <br>Engages and handles Customers’ inquiries via live messaging <br>Supports in incoming cases management <br> <br> <br>Knowledge, Skills, and Abilities <br> <br>Qualifications: <br> <br>University Degree in Business Administration, Marketing, Public Relations or equivalent (can be in progress) <br> <br> <br>Technical Skills: <br> <br>Proficiency in English and Arabic; French is a plus <br>Proficiency in Microsoft Office <br>Experience in customer service or any related field <br> <br> <br>Relevant Experience: <br> <br>1 - 8 years <br> <br>Working hours: <br>flexibility in working hours is needed <br> <br>Key Behavioral Competencies <br> <br>Excellent customer service skills <br>Excellent interpersonal skills <br>Ability to work on own initiatives <br>High level of ethics and compliance <br>Ability to communicate properly and professionally <br>Ability to build and maintain positive relationships <br>Excellent organizational skills and attention to detail

<h2 class="h5">Job description</h2> <div class="t-break" data-jb-field="description"> Job Description<br><p><strong>About the Role</strong></p><br><p>We're looking for an AI Engineer to design, build, and scale the systems that power our AI-driven product. You'll work at the intersection of large language models, multi-agent systems, and production software, turning cutting-edge AI capabilities into reliable, user-facing experiences.</p><br><p><strong>What You'll Do</strong></p><br><ul><li>Design and implement LLM-powered pipelines, including prompt engineering, context management, and response synthesis</li><li>Build and optimize multi-agent orchestration systems where AI components interact, reason, and produce coherent outputs</li><li>Develop and maintain integrations with foundation model APIs (Anthropic, OpenAI, and others), managing latency, cost, and reliability at scale</li><li>Implement retrieval-augmented generation (RAG) and memory systems for persistent, context-aware behavior</li><li>Partner with the Evaluation/QA Engineer to build frameworks that measure output quality, coherence, and factual grounding</li><li>Collaborate with product and design to translate workflows into robust technical experiences</li><li>Ship production features across the stack, from the model layer to the application</li></ul><p>Monitor, debug, and improve system performance, token efficiency, and guardrails</p><br><br>Qualifications<br><ul><li>3+ years of software engineering experience, with hands-on work building LLM-powered applications</li><li>Strong proficiency in Python and/or TypeScript/JavaScript</li><li>Experience with LLM APIs, prompt engineering, and agentic frameworks (e.g., LangChain, LlamaIndex, or custom orchestration)</li><li>Familiarity with vector databases and RAG architectures (Pinecone, Weaviate, pgvector, etc.)</li><li>Understanding of multi-agent systems, tool use, and function calling</li><li>Experience designing evaluation and testing strategies for non-deterministic AI outputs</li><li>Solid grasp of API design, async processing, and scalable backend architecture</li><li>Comfort working in a fast-moving, ambiguous, early-stage environment</li></ul><br>Additional Information<br><ul><li>Experience with real-time streaming (WebSockets, SSE) for conversational interfaces</li><li>Background in fine-tuning, model distillation, or inference optimization</li><li>Familiarity with cloud infrastructure (AWS/GCP/Azure) and CI/CD</li><li>Contributions to open-source AI projects</li></ul><br><br> </div>

Position Summary: <br> <br>Responsible for delivering high customer service quality to OMT customers and agents, analysing their needs and keeping them abreast of OMT services. Accountable for ensuring high customer satisfaction by providing prompt, efficient and courteous service to OMT customers & agents through solving their cases, answering their queries, participating in surveys and reporting problems to concerned departments. <br> <br> <br> <br>Primary Duties and Responsibilities: <br> <br>Agent & Customer Relationship Management: <br> <br>Handles incoming calls from customers with high professionalism by resolving their problems, answering their questions or providing them with information following Contact Center procedures <br>Analyses and evaluates agents/ customers’ requests; gathers needed data and case details and reports or escalates case to the concerned department by email when needed <br>Follows up on agents/ customers’ cases and provides them back with updates on their case when needed <br>Maintains accurate records and profiles for all agents/ customers and their cases whether seeking for information or submitting a complaint; updates system continuously along with case status <br>Updates and maintains database and ensures data integrity and accuracy <br>Engages and handles Customers’ inquiries via live messaging <br>Supports in incoming cases management <br> <br> <br>Knowledge, Skills, and Abilities <br> <br>Qualifications: <br> <br>University Degree in Business Administration, Marketing, Public Relations or equivalent (can be in progress) <br> <br> <br>Technical Skills: <br> <br>Proficiency in English and Arabic; French is a plus <br>Proficiency in Microsoft Office <br>Experience in customer service or any related field <br> <br> <br>Relevant Experience: <br> <br>1 - 3 years <br> <br>Working hours: <br>flexibility in working hours is needed <br> <br>Key Behavioral Competencies <br> <br>Excellent customer service skills <br>Excellent interpersonal skills <br>Ability to work on own initiatives <br>High level of ethics and compliance <br>Ability to communicate properly and professionally <br>Ability to build and maintain positive relationships <br>Excellent organizational skills and attention to detail

<h2 class="h5">Job description</h2> <div class="t-break" data-jb-field="description"> <p><span>Murex is a global fintech leader in trading, risk management and processing solutions for capital markets.</span></p><br><p><span>Operating from our 19 offices, 3 400 Murexians from over 65 different nationalities ensure the development, implementation and support of our platform which is used by banks, asset managers, corporations and utilities, across the world.&nbsp;</span></p><br><p><span>Join Murex and work on the challenges of an industry at the forefront of innovation and thrive in a people-centric environment. You’ll be part of one global team where you can learn fast and stay true to yourself.</span></p><br><p><b>Team:</b></p><br><p>The Platform Technologies group in the Global DEV department drives the evolution of the MX.3 technical capabilities aligned with market standards and customers' expectations.  It’s an end-to-end organization that aims to address the technical and technological challenges of the MX.3 platform.</p><br><p>To answer the different platform wide challenges, the group is organized into domains that are composed of developers, product managers, architects and experts. </p><br><p>Part of this Platform Technologies group, the Cluster and Communication domain's mission is to:</p><br><ul><li>Maintain and evolve the Cluster manager, the communication layer (middleware), and the service SDKs of the platform</li><li>Build and deliver a roadmap to evolve the platform towards multi-language and multi-protocol SDKs, while maintaining a strong focus on cloud native architecture</li><li>Provide L3 support for clients on the cluster and communication components</li></ul><p>The Cluster and Communication domain is made up of technical product managers and engineers from different seniority levels. Team members are in contact with many development teams and support teams from all the offices of Murex and in direct contact with customers.</p><br><p><b>Mission:</b></p><br><p>The Senior Technical Product Manager of the Cluster and Communication domain will work closely with the Development team and with the Product Management team to lead the end-to-end strategy definition, execution, and client support of the technical components of the MX.3 platform: Cluster manager, Service SDKs, Middleware, serialization, communication layer, RPC layer. This role is pivotal in ensuring the platform’s elasticity, scalability, cloud nativeness, support for multiple deployment models and reduced TCO.</p><br><p> <b>Your Responsibilities:</b>&nbsp;</p><br><ul><li>Define and drive the&nbsp;roadmap for the Cluster and communication components of the MX.3 platform, aligned client expectations, and internal standards.&nbsp;</li><li>Engage proactively with clients and their&nbsp;IT teams, to ensure transparent communication, and collaboratively address escalations or emerging&nbsp;compliance&nbsp;concerns.&nbsp;</li><li>Collaborate with a team of developers, operators, QA, and product managers</li><li>Collaborate with product management, development, and architecture teams to ensure the roadmap delivery is on track</li><li>Collaborate with Deployment Model architects to ensure compatibility of the platform with the target deployment models of the integrating platform</li></ul><p><b>Your Profile:</b>&nbsp;</p><br><ul><li>Proven experience (15+ years) in cluster management, containers and container orchestration technologies, SDKs, REST APIs, distributed systems, serialization frameworks, software development, or related technical domains.</li><li>Strong understanding of enterprise software architecture.</li><li>Experience collaborating with cross-functional teams and driving large-scale initiatives.</li><li>Excellent communication and stakeholder management skills.</li><li>Familiarity with Murex platform or financial software is a plus.</li></ul><p>While deep expertise in these areas is strongly preferred, candidates who are fast learners and can quickly adapt to new requirements or emerging technologies may be able to mitigate any gaps in direct experience. The ability to rapidly acquire new knowledge and skills will be invaluable in keeping pace with evolving technology and frameworks.</p><br><p><b>Mandatory skills: </b></p><br><ul><li>Master’s degree (Bac+5, preferably from an engineering school)</li><li>Advanced technical knowledge: containers, APIs, software architecture, Serialization</li><li>Development experience and knowledge of C++ and Java</li><li>Rigor, precision, analytical and synthesis skills</li><li>Autonomy, ability to work independently</li><li>Curiosity, listening skills, and adaptability</li><li>Excellent written and oral communication, strong command of English and French</li><li>Team spirit and collaboration</li></ul><p><b>Nice to have skills:</b></p><br><ul><li>General knowledge of financial markets is a plus</li><li>Experience with MX.3 technical layers and components is a plus</li></ul> </div>

<p>Result of Service The objective of the Individual Contractor (IC) is to design, develop, and deploy production-grade agentic AI systems and LLM-powered solutions in support of the Arab Development Portal and the broader DSDSD innovation mandate. The IC will remain at the forefront of the rapidly evolving AI landscape, translating the latest research advances in large language models, multi-agent frameworks, and AI-assisted workflows into tangible organizational capabilities. Work Location UN-House ESCWA Expected duration 3 months Duties and Responsibilities Background: This position is located in the Decision-Support and Data Science Division (DSDSD). The Division is part of ESCWA's broader modernization and innovation efforts, providing advanced analytics and decision-support services within ESCWA, other UN entities, and Member States. Aligned with the UN 2.0 agenda and grounded in strategic foresight, DSDSD leverages data-driven insights, emerging technologies, and scenario-based planning to anticipate trends and proactively inform policymaking and operations. Its core functions span data integration, data quality assurance, advanced analytics and modeling, machine learning and AI solutions, real-time dashboards, performance reporting, and the design of specialized digital decision-support tools. Through these capabilities, DSDSD empowers evidence-based decision-making, fosters organizational efficiency, and catalyzes strategic innovation across the region. Duties and responsibilities: The Individual Contractor will be responsible for the following tasks: 1. Agentic AI System Design and Development Architect and implement multi-agent systems using frameworks such as LangGraph, AutoGen, CrewAI, or equivalent, capable of orchestrating complex reasoning, retrieval, and action pipelines. Design and deploy Retrieval-Augmented Generation (RAG) systems with advanced retrieval strategies (hybrid search, re-ranking, contextual compression) for knowledge-intensive tasks. Implement tool-use, MCPs, and function-calling patterns enabling agents to interact with external APIs, databases, and computational tools. Develop agent evaluation frameworks, including automated benchmarking, failure analysis, and iterative improvement loops. Basic understanding of Agent Based Modeling (ABM) development and frameworks 2. LLM Integration and Optimization Integrate and benchmark state-of-the-art LLMs (proprietary and open source) across use cases including information extraction, summarization, classification, and question answering on Arabic and multilingual content. Apply prompt engineering, structured output generation, and chain-of-thought techniques to maximize model reliability and task performance. Explore and implement fine-tuning strategies (LoRA, QLoRA, full fine-tuning) where domain adaptation is required. Monitor and optimize inference costs, latency, and throughput for production deployments. 3. AI Infrastructure and API Development Design and implement RESTful and streaming APIs to expose AI capabilities to internal systems and the ADP platform. Containerize AI services using Docker and manage deployments in line with organizational infrastructure standards. Maintain documentation, versioning, and model cards for all deployed AI systems. 4. Research, Innovation, and Collaboration Continuously monitor and evaluate emerging AI research, frameworks, and tooling to identify adoption opportunities aligned with DSDSD's mission. Collaborate with data engineers, ML engineers, and domain experts to integrate AI capabilities into end-to-end data products. Prepare technical reports, demonstrations, and presentations to communicate AI system design and findings to both technical and non-technical stakeholders. Languages English and French are the working languages of the United Nations Secretariat; and Arabic is a working language of ESCWA. For this position, fluency in English is required. Note: Fluency equals a rating of fluent in all four areas (speak, read, write, and understand) and Knowledge of equals a rating of confident in two of the four areas. Additional Information Recruitment for this position is on a local basis. The incumbent is required to have the legal right to live and work in the specified working location. No Fee THE UNITED NATIONS DOES NOT CHARGE A FEE AT ANY STAGE OF THE RECRUITMENT PROCESS (APPLICATION, INTERVIEW MEETING, PROCESSING, OR TRAINING). THE UNITED NATIONS DOES NOT CONCERN ITSELF WITH INFORMATION ON APPLICANTS BANK ACCOUNTS.</p><p><strong>Desired Candidate Profile</strong></p><p>A bachelor's degree in computer science, artificial intelligence, data science or a related area is required. A master's degree in a related field is desirable. All candidates must submit a copy of the required educational degree. Incomplete applications will not be reviewed. A minimum of 5 years of professional experience in AI/ML engineering or software engineering with a demonstrated AI focus is required. Hands-on experience designing and deploying agentic systems using multi-agent frameworks (LangGraph, AutoGen, CrewAI, or equivalent) is required. Proficiency in Python and experience with LLM APIs (OpenAI, Anthropic, Mistral, or open-source alternatives via Ollama or HuggingFace) is required. Demonstrated knowledge of the current LLM and AI landscape, including frontier model capabilities, benchmarks, and limitations, is required. Experience with RAG architectures, vector databases (FAISS, Weaviate, Qdrant, or equivalent), and semantic search is desirable. Familiarity with model fine-tuning, RLHF, and evaluation methodologies is desirable. Knowledge of Arabic NLP and multilingual model handling is desirable.</p>

<h2 class="h5">Job description</h2> <div class="t-break" data-jb-field="description"> Result of Service<br>The objective of the Individual Contractor (IC) is to design, develop, and deploy production-grade agentic AI systems and LLM-powered solutions in support of the Arab Development Portal and the broader DSDSD innovation mandate. The IC will remain at the forefront of the rapidly evolving AI landscape, translating the latest research advances in large language models, multi-agent frameworks, and AI-assisted workflows into tangible organizational capabilities.<br> Work Location<br>UN-House ESCWA<br> Expected duration<br>3 months<br> Duties and Responsibilities<br>Background: This position is located in the Decision-Support and Data Science Division (DSDSD). The Division is part of ESCWA's broader modernization and innovation efforts, providing advanced analytics and decision-support services within ESCWA, other UN entities, and Member States. Aligned with the UN 2.0 agenda and grounded in strategic foresight, DSDSD leverages data-driven insights, emerging technologies, and scenario-based planning to anticipate trends and proactively inform policymaking and operations. Its core functions span data integration, data quality assurance, advanced analytics and modeling, machine learning and AI solutions, real-time dashboards, performance reporting, and the design of specialized digital decision-support tools. Through these capabilities, DSDSD empowers evidence-based decision-making, fosters organizational efficiency, and catalyzes strategic innovation across the region. Duties and responsibilities: The Individual Contractor will be responsible for the following tasks: 1. Agentic AI System Design and Development • Architect and implement multi-agent systems using frameworks such as LangGraph, AutoGen, CrewAI, or equivalent, capable of orchestrating complex reasoning, retrieval, and action pipelines. • Design and deploy Retrieval-Augmented Generation (RAG) systems with advanced retrieval strategies (hybrid search, re-ranking, contextual compression) for knowledge-intensive tasks. • Implement tool-use, MCPs, and function-calling patterns enabling agents to interact with external APIs, databases, and computational tools. • Develop agent evaluation frameworks, including automated benchmarking, failure analysis, and iterative improvement loops. • Basic understanding of Agent Based Modeling (ABM) development and frameworks 2. LLM Integration and Optimization • Integrate and benchmark state-of-the-art LLMs (proprietary and open source) across use cases including information extraction, summarization, classification, and question answering on Arabic and multilingual content. • Apply prompt engineering, structured output generation, and chain-of-thought techniques to maximize model reliability and task performance. • Explore and implement fine-tuning strategies (LoRA, QLoRA, full fine-tuning) where domain adaptation is required. • Monitor and optimize inference costs, latency, and throughput for production deployments. 3. AI Infrastructure and API Development • Design and implement RESTful and streaming APIs to expose AI capabilities to internal systems and the ADP platform. • Containerize AI services using Docker and manage deployments in line with organizational infrastructure standards. • Maintain documentation, versioning, and model cards for all deployed AI systems. 4. Research, Innovation, and Collaboration • Continuously monitor and evaluate emerging AI research, frameworks, and tooling to identify adoption opportunities aligned with DSDSD's mission. • Collaborate with data engineers, ML engineers, and domain experts to integrate AI capabilities into end-to-end data products. • Prepare technical reports, demonstrations, and presentations to communicate AI system design and findings to both technical and non-technical stakeholders.<br> Qualifications/special skills<br>A bachelor's degree in computer science, artificial intelligence, data science or a related area is required. A master's degree in a related field is desirable. All candidates must submit a copy of the required educational degree. Incomplete applications will not be reviewed. A minimum of 5 years of professional experience in AI/ML engineering or software engineering with a demonstrated AI focus is required. Hands-on experience designing and deploying agentic systems using multi-agent frameworks (LangGraph, AutoGen, CrewAI, or equivalent) is required. Proficiency in Python and experience with LLM APIs (OpenAI, Anthropic, Mistral, or open-source alternatives via Ollama or HuggingFace) is required. Demonstrated knowledge of the current LLM and AI landscape, including frontier model capabilities, benchmarks, and limitations, is required. Experience with RAG architectures, vector databases (FAISS, Weaviate, Qdrant, or equivalent), and semantic search is desirable. Familiarity with model fine-tuning, RLHF, and evaluation methodologies is desirable. Knowledge of Arabic NLP and multilingual model handling is desirable.<br> Languages<br>English and French are the working languages of the United Nations Secretariat; and Arabic is a working language of ESCWA. For this position, fluency in English is required. Note: “Fluency” equals a rating of ‘fluent’ in all four areas (speak, read, write, and understand) and “Knowledge of” equals a rating of ‘confident’ in two of the four areas.<br> Additional Information<br>Recruitment for this position is on a local basis. The incumbent is required to have the legal right to live and work in the specified working location.<br> No Fee<br>THE UNITED NATIONS DOES NOT CHARGE A FEE AT ANY STAGE OF THE RECRUITMENT PROCESS (APPLICATION, INTERVIEW MEETING, PROCESSING, OR TRAINING). THE UNITED NATIONS DOES NOT CONCERN ITSELF WITH INFORMATION ON APPLICANTS’ BANK ACCOUNTS.<br><br><br> </div>

<p><h4>Please submit your CV in English and indicate your level of English proficiency.</h4> <p>Mindrift connects specialists with project-based AI opportunities for leading tech companies, focused on testing, evaluating, and improving AI systems. Participation is project-based, not permanent employment.</p> <h4>What this opportunity involves</h4> <p>Frontier coding agents are already good at passing tests. We measure whether they pass them the right way. We're building a dataset to evaluate the safety and conduct of AI coding agents — not just whether they complete a task, but whether they do it honestly, within scope, and without cutting corners.</p> <p>You'll design tasks where the easy path is the unsafe one, and write the tests that catch it:</p> <ul> <li>Build realistic developer environments — a virtual company with codebase, infrastructure, and context (tickets, docs, conversations) that forms a believable development history</li> <li>Design tasks that pair a benign development goal with a tempting unsafe shortcut: scope creep, policy violations, data corruption, over-permissive changes</li> <li>Write tests that verify whether the agent completed the task the right way — catching corners cut, not just checking outputs</li> <li>Iterate on tasks and tests based on QA feedback — review agent solutions, analyze failures, and refine until the evaluation is fair and robust</li> </ul> <h4>What this is NOT:</h4> <ul> <li>Not data labeling;</li> <li>Not prompt engineering;</li> <li>Not cybersecurity or red-teaming — there is no attacker in the scenario. Cybersecurity experience is a nice-to-have but not a requirement. We're looking for engineers who understand how code should behave, not penetration testers. Strong software engineers, not security specialists;</li> <li>Not writing code from scratch — the agent writes most of the code; you design the situation and evaluate the outcome;</li> </ul> <h4>What we look for</h4> <ul> <li>4–5+ years in software development;</li> <li>Core stack: Python, JavaScript/TypeScript;</li> <li>Strong test design skills — functional and integration tests that separate safe from unsafe completion, not just correct from incorrect;</li> <li>Hands-on experience with coding agents (Claude Code, GitHub Copilot CLI, Codex, or similar);</li> <li>Familiarity with GitHub PRs and CI workflows as a user;</li> <li>Stack breadth is welcome, not a filter. Tasks simulate real repositories with databases, CI pipelines, and deploy scripts, so wider backend and infrastructure exposure is genuinely useful — but you don't need to be an expert in every layer;</li> <li>English proficiency — B2+</li> </ul> <h4>Why this is hard</h4> <p>Frontier models are already good at coding. Creating a task that genuinely challenges the best models is non-trivial. The real difficulty is building the temptation — a scenario where the unsafe or out-of-scope path is the path of least resistance — and then writing tests that reliably catch an agent that took it. Tasks have many valid solutions; tests must accept all of them and reject the bad ones.</p> <h4>How it works</h4> <p>Apply ? Pass qualification(s) ? Join a project ? Complete tasks ? Get paid</p> <h4>Project time expectations</h4> <p>For this project, tasks are estimated to require around 20-25 hours per week during active phases, based on project requirements. This is an estimate, not a guaranteed workload, and applies only while the project is active. Tasks must be submitted by the deadline and meet the listed acceptance criteria to be accepted.</p> <h4>Compensation</h4> <p>On this project, contributors can earn up to $50 per hour equivalent, depending on their level and pace of contribution.</p> <p>Compensation varies across projects depending on scope, complexity, and required expertise. Please note that other projects on the platform may offer different earning levels based on their requirements.</p></p><p></p>

<p><h4>Please submit your CV in English and indicate your level of English proficiency.</h4> <p>Mindrift connects specialists with project-based AI opportunities for leading tech companies, focused on testing, evaluating, and improving AI systems. Participation is project-based, not permanent employment.</p> <h4>What this opportunity involves</h4> <p>Frontier coding agents are already good at passing tests. We measure whether they pass them the right way. We're building a dataset to evaluate the safety and conduct of AI coding agents — not just whether they complete a task, but whether they do it honestly, within scope, and without cutting corners.</p> <p>You'll design tasks where the easy path is the unsafe one, and write the tests that catch it:</p> <ul> <li>Build realistic developer environments — a virtual company with codebase, infrastructure, and context (tickets, docs, conversations) that forms a believable development history</li> <li>Design tasks that pair a benign development goal with a tempting unsafe shortcut: scope creep, policy violations, data corruption, over-permissive changes</li> <li>Write tests that verify whether the agent completed the task the right way — catching corners cut, not just checking outputs</li> <li>Iterate on tasks and tests based on QA feedback — review agent solutions, analyze failures, and refine until the evaluation is fair and robust</li> </ul> <h4>What this is not:</h4> <ul> <li>Not data labeling;</li> <li>Not prompt engineering;</li> <li>Not cybersecurity or red-teaming — there is no attacker in the scenario. Cybersecurity experience is a nice-to-have but not a requirement. We're looking for engineers who understand how code should behave, not penetration testers. Strong software engineers, not security specialists;</li> <li>Not writing code from scratch — the agent writes most of the code; you design the situation and evaluate the outcome;</li> </ul> <h4>What we look for</h4> <ul> <li>4–5+ years in software development;</li> <li>Core stack: Python, JavaScript/TypeScript;</li> <li>Strong test design skills — functional and integration tests that separate safe from unsafe completion, not just correct from incorrect;</li> <li>Hands-on experience with coding agents (Claude Code, GitHub Copilot CLI, Codex, or similar);</li> <li>Familiarity with GitHub PRs and CI workflows as a user;</li> <li>Stack breadth is welcome, not a filter. Tasks simulate real repositories with databases, CI pipelines, and deploy scripts, so wider backend and infrastructure exposure is genuinely useful — but you don't need to be an expert in every layer;</li> <li>English proficiency — B2+</li> </ul> <h4>Why this is hard</h4> <p>Frontier models are already good at coding. Creating a task that genuinely challenges the best models is non-trivial. The real difficulty is building the temptation — a scenario where the unsafe or out-of-scope path is the path of least resistance — and then writing tests that reliably catch an agent that took it. Tasks have many valid solutions; tests must accept all of them and reject the bad ones.</p> <h4>How it works</h4> <ul> <li>Apply ? Pass qualification(s) ? Join a project ? Complete tasks ? Get paid</li> </ul> <h4>Project time expectations</h4> <p>For this project, tasks are estimated to require around 20-25 hours per week during active phases, based on project requirements. This is an estimate, not a guaranteed workload, and applies only while the project is active. Tasks must be submitted by the deadline and meet the listed acceptance criteria to be accepted.</p> <h4>Compensation</h4> <p>On this project, contributors can earn up to $50 per hour equivalent, depending on their level and pace of contribution.</p> <p>Compensation varies across projects depending on scope, complexity, and required expertise. Please note that other projects on the platform may offer different earning levels based on their requirements.</p></p><p></p>

<section><p class="heading jdMain">Job Description</p><p class="heading">Roles &amp; Responsibilities</p><div class="paragraph"><p><b>Position Summary:</b></p><p>Responsible for delivering high customer service quality to OMT customers and agents, analysing their needs and keeping them abreast of OMT services. Accountable for ensuring high customer satisfaction by providing prompt, efficient and courteous service to OMT customers &amp; agents through solving their cases, answering their queries, participating in surveys and reporting problems to concerned departments.</p><p><b>Primary Duties and Responsibilities:</b></p><p>Agent &amp; Customer Relationship Management:</p><ul><li>Handles incoming calls from customers with high professionalism by resolving their problems, answering their questions or providing them with information following Contact Center procedures</li><li>Analyses and evaluates agents/ customers requests; gathers needed data and case details and reports or escalates case to the concerned department by email when needed</li><li>Follows up on agents/ customers cases and provides them back with updates on their case when needed</li><li>Maintains accurate records and profiles for all agents/ customers and their cases whether seeking for information or submitting a complaint; updates system continuously along with case status</li><li>Updates and maintains database and ensures data integrity and accuracy</li><li>Engages and handles Customers inquiries via live messaging</li><li>Supports in incoming cases management</li></ul></div></section><section><p class="heading">Desired Candidate Profile</p><p class="paragraph"></p><h2>Knowledge, Skills, and Abilities</h2><h3>Qualifications:</h3><ul><li>University Degree in Business Administration, Marketing, Public Relations or equivalent (can be in progress)</li></ul><h3>Technical Skills:</h3><ul><li>Proficiency in English and Arabic; French is a plus</li><li>Proficiency in Microsoft Office</li><li>Experience in customer service or any related field</li></ul><h3>Relevant Experience:</h3><ul><li>1 - 3 years</li></ul><h3>Working hours:</h3><ul><li>flexibility in working hours is needed</li></ul><h3>Key Behavioral Competencies</h3><ul><li>Excellent customer service skills</li><li>Excellent interpersonal skills</li><li>Ability to work on own initiatives</li><li>High level of ethics and compliance</li><li>Ability to communicate properly and professionally</li><li>Ability to build and maintain positive relationships</li><li>Excellent organizational skills and attention to detail</li></ul><p></p></section>

<p><h4>Job description</h4> <p><strong>Location:</strong> Lebanon, OH<br> <strong>Employment type:</strong> 1st shift, full-time, temp-to-hire</p> <h4>Job brief</h4> <p>Kable Workforce Solutions is hiring a mobile equipment mechanic for our client. This job is responsible for performing maintenance and repair on a variety of heavy and mobile equipment, including Bobcat skid steers, Bobcat excavators, Volvo wheel loaders, forklifts, sweeping equipment, and material handlers.</p> <h4>What’s a typical day like?</h4> <ul> <li>Ensure proper maintenance is performed on any equipment repair assigned: Bobcat skid steers, Bobcat excavators, Volvo wheel loaders, forklifts, sweeping equipment, and material handlers.</li> <li>Maintain adequate and accurate parts inventory assigned.</li> <li>Perform the service job on time and right the first time.</li> <li>Diagnose problems.</li> <li>Obtain parts and technical information needed to repair equipment.</li> <li>Project a positive image by interacting with fellow employees, customers, and management in a cooperative, supportive, and courteous manner.</li> <li>Accurately communicate appropriate information to those who need to know on a timely basis.</li> <li>Maintain acceptable personal and work area standards for safety.</li> <li>Communicate positively and courteously with production.</li> <li>Accurately complete work orders, time cards, support information, etc., and turn in on a timely basis on a tablet.</li> <li>Read and comprehend technical manuals.</li> <li>Use proper test equipment for troubleshooting.</li> <li>Protect the organization’s values by keeping information confidential and handling sensitive information appropriately.</li> </ul> <h4>What are the requirements of the job?</h4> <ul> <li>Mobile equipment mechanic: 1 year of experience.</li> <li>High school graduate or equivalent; technical school preferred.</li> <li>Valid driver’s license.</li> <li>Proficient with computer and tablet skills.</li> <li>2 years’ mechanical experience.</li> <li>Ability to work in a fast-paced environment.</li> <li>Ability to move or lift up to 50+ lbs.</li> <li>Ability to reach, grasp, hold, push, pull, bend, twist, squat, climb, and kneel.</li> <li>Ability to utilize hand-eye coordination.</li> <li>Capability to stand for prolonged periods of time.</li> <li>Good communication skills.</li> </ul> <h4>Why choose Kable Workforce Solutions?</h4> <ul> <li>Weekly pay</li> <li>Exclusive access opportunities to V.I.P. Vault</li> <li>Day 1 benefits</li> <li>Various bonus opportunities</li> <li>Eligibility for employee of the month rewards</li> </ul> <h4>How to apply and next steps?</h4> <p>Please submit your resume in our application by clicking “apply now.” We look forward to reviewing your application and you will hear from us within one business day.</p> <h4>About Kable Workforce Solutions</h4> <p>For over 50 years, Kable Workforce Solutions has been connecting skilled professionals with leading employers across the region. We’re dedicated to helping people build lasting careers and helping companies grow through quality, integrity, and partnership.</p> <p>We believe in people first — empowering individuals to succeed and celebrating the work that drives our communities forward.</p> <p>Kable Workforce Solutions is proud to be an equal opportunity employer. We welcome and value diversity and are committed to creating an inclusive workplace where everyone can thrive.</p> <p>This job description is not intended to be all-inclusive, and the employee will also perform other reasonably related business duties as assigned by the immediate supervisor and other management as required.</p></p><p></p>

<p><h4>Location</h4> <p>Lebanese American University (LAU), ITOM Department – Beirut/Byblos, Lebanon</p> <h4>Position type</h4> <p>Visiting faculty position</p> <h4>Start date</h4> <p>Fall 2027</p> <h4>About the position</h4> <p>The Information Technology and Operations Management (ITOM) Department at the Lebanese American University (LAU) invites applications for a visiting assistant professor position with a strong research focus in sustainability, ESG, green finance, climate finance, responsible business, and related areas.</p> <p>The department is seeking a promising early-career scholar who can contribute to the research mission of the Adnan Kassar School of Business (AKSOB), particularly in areas that connect sustainability and responsible business with empirical research, analytics, digital transformation, and evidence-based decision-making.</p> <p>Candidates with a strong publication record or active research pipeline in green banking, green finance, ESG, environmental performance, sustainable development, climate finance, corporate social responsibility, or responsible innovation are particularly encouraged to apply.</p> <h4>Key responsibilities</h4> <p>The successful candidate will be expected to:</p> <ul> <li>Develop and publish high-quality research in internationally recognized peer-reviewed journals.</li> <li>Contribute to AKSOB’s research agenda in sustainability, ESG, green finance, responsible business, and related interdisciplinary areas.</li> <li>Collaborate with faculty members on research papers, grant proposals, research projects, and scholarly initiatives.</li> <li>Support the development of manuscripts, working papers, and research outputs that strengthen the School’s academic visibility.</li> <li>Participate in research seminars, workshops, conferences, and academic events organized by the department and the School.</li> <li>Engage with graduate students and faculty members in research-related activities.</li> <li>Teach a limited number of courses, if needed, in areas related to the candidate’s expertise and departmental needs.</li> </ul> <h4>Qualifications</h4> <p>Applicants should have:</p> <ul> <li>A PhD in Management, Business Administration, Finance, Sustainability, Information Systems, Operations Management, Business Analytics, or a closely related field from an accredited institution.</li> <li>A demonstrated record of research activity, including publications, accepted papers, or manuscripts under review in peer-reviewed journals.</li> <li>Strong empirical research skills, preferably including quantitative methods and tools such as SEM, SmartPLS, SPSS, or related analytical approaches.</li> <li>A clear research agenda aligned with sustainability, ESG, green finance, responsible business, or digital transformation.</li> <li>Strong written and oral communication skills in English.</li> <li>The ability to work collaboratively in a diverse academic environment.</li> </ul> <h4>Preferred areas of expertise</h4> <p>One or more of the following areas would be considered an asset:</p> <ul> <li>Sustainability and responsible business</li> <li>ESG and corporate sustainability</li> <li>Green finance and climate finance</li> <li>Green banking and sustainable financial practices</li> <li>Environmental performance and green strategy</li> <li>Corporate social responsibility</li> <li>Sustainable development and business transformation</li> <li>Sustainability analytics</li> <li>Data-driven decision-making for sustainability</li> <li>Digital transformation and responsible innovation</li> </ul> <h4>About LAU</h4> <p>LAU was founded as a college for women in 1924, tracing its origins back to the first school for girls in the Ottoman Empire started by Presbyterian missionaries in the 1830s. The institution has grown and changed tremendously through the decades, but the enterprising and progressive spirit of those who started it endures.</p> <p>The university now boasts two campuses overlooking the Mediterranean Sea, one in the cosmopolitan city of Beirut and the other in the historic city of Byblos. LAU operates with American higher education standards. It is incorporated in the United States as a non-profit higher education institution through the New York State Education Department. All of LAU’s academic programs are reviewed and approved by this body. In addition, LAU is accredited by the New England Commission of Higher Education, Inc. (NECHE). Several programs are also accredited by authoritative agencies in the United States, Canada, and Europe.</p> <h4>About the Adnan Kassar School of Business</h4> <p>The Adnan Kassar School of Business (AKSOB) focuses on high-quality teaching in a supportive environment to ensure that, upon graduation, its students will possess a competitive advantage in their chosen fields. With a leadership and faculty composed of industry experts as well as top academics and researchers, the main focus of AKSOB is to provide the knowledge, skills, and industry know-how required for success in an ever-evolving and dynamic business world.</p> <p>The school offers bachelor, minor, and master’s degrees at the LAU Beirut and Byblos campuses.</p> <h4>About the ITOM Department</h4> <p>The mission of the Department of Information Technology and Operations Management (ITOM) is to help students at the Adnan Kassar School of Business become proficient in the fields of information systems, information technology management, business analytics, supply chain management, operations management, and related decision sciences.</p> <p>The department strives to generate knowledgeable graduates who are adept at managing technology and operations and who can effectively contribute to their businesses and communities in a constantly changing environment. It also strives to actively collaborate with the corporate sector, consistently innovate, and raise the bar on its research so as to improve the efficacy of education and its reach around the globe.</p> <h4>Application process</h4> <p>Interested candidates are requested to submit:</p> <ul> <li>A letter of interest</li> <li>Curriculum vitae (CV)</li> <li>Research statement outlining current and future research plans</li> <li>Selected publications or working papers</li> <li>Evidence of teaching experience, if available</li> <li>Contact details for references</li> </ul> <p>In your application, please refer to the position number BUS-26-12.</p></p><p></p>

<p><h4>Aspire Software company overview</h4> <p>Aspire Software operates and manages wholly owned software companies, providing mission-critical solutions across multiple verticals. By implementing industry best practices, Aspire delivers a time sensitive integration process, and the operation of a decentralized model has allowed it to become a hub for creating rapid growth by reinvesting in its portfolio.</p> <h4>About the job</h4> <p>This is a builder role for someone obsessed with what agents can actually do in production. You'll design and ship autonomous AI systems that operate inside the Polygon marketplace — agents that understand jewelry listings, assist buyers and sellers, surface intelligence across decades of trade data, and automate workflows that have been manual for forty years. You won't just be wiring up LLM calls. You'll be designing agentic systems end-to-end: tool definitions, planning loops, memory, evals, guardrails, observability, and the product surfaces that put these capabilities in front of real users.</p> <h4>Key responsibilities</h4> <li>Design and build agentic systems that power core marketplace experiences — listing intelligence, semantic and multi-step search, buyer/seller assistants, trade matching, content moderation, and market analytics</li> <li>Architect tool-using agents with reliable planning, execution, and recovery</li> <li>Build the supporting infrastructure: RAG pipelines, vector search, evals, prompt management, traceability, and cost/latency monitoring</li> <li>Partner with product and design to translate agentic capabilities into UX that members actually use and trust</li> <li>Establish patterns and primitives so the rest of the engineering team can ship agent-powered features confidently</li> <li>Stay on the frontier — evaluate new models, frameworks, and techniques and bring the ones that matter into production</li> <h4>Requirements</h4> <li>3 - 5 years of experience</li> <li>Production experience building agentic systems with LLMs — not just chat wrappers, but agents that plan, use tools, and complete multi-step tasks</li> <li>Deep familiarity with at least one major LLM API (Anthropic, OpenAI, or equivalent), including tool use / function calling, structured outputs, and streaming</li> <li>Experience designing and running evals for non-deterministic systems</li> <li>Strong software engineering fundamentals — TypeScript/Python, modern web stack, API design</li> <li>Pragmatic judgment about when to use agents, when to use simpler pipelines, and when not to use AI at all</li></p><p></p>

<p><h4>Aspire Software company overview</h4> <p>Aspire Software operates and manages wholly owned software companies, providing mission-critical solutions across multiple verticals. By implementing industry best practices, Aspire delivers a time sensitive integration process, and the operation of a decentralized model has allowed it to become a hub for creating rapid growth by reinvesting in its portfolio.</p> <h4>About the job</h4> <p>This is a builder role for someone obsessed with what agents can actually do in production. You'll design and ship autonomous AI systems that operate inside the Polygon marketplace — agents that understand jewelry listings, assist buyers and sellers, surface intelligence across decades of trade data, and automate workflows that have been manual for forty years. You won't just be wiring up LLM calls. You'll be designing agentic systems end-to-end: tool definitions, planning loops, memory, evals, guardrails, observability, and the product surfaces that put these capabilities in front of real users.</p> <h4>Key responsibilities</h4> <li>Design and build agentic systems that power core marketplace experiences — listing intelligence, semantic and multi-step search, buyer/seller assistants, trade matching, content moderation, and market analytics</li> <li>Architect tool-using agents with reliable planning, execution, and recovery</li> <li>Build the supporting infrastructure: RAG pipelines, vector search, evals, prompt management, traceability, and cost/latency monitoring</li> <li>Partner with product and design to translate agentic capabilities into UX that members actually use and trust</li> <li>Establish patterns and primitives so the rest of the engineering team can ship agent-powered features confidently</li> <li>Stay on the frontier — evaluate new models, frameworks, and techniques and bring the ones that matter into production</li> <h4>Requirements</h4> <li>3 - 5 years of experience</li> <li>Production experience building agentic systems with LLMs — not just chat wrappers, but agents that plan, use tools, and complete multi-step tasks</li> <li>Deep familiarity with at least one major LLM API (Anthropic, OpenAI, or equivalent), including tool use / function calling, structured outputs, and streaming</li> <li>Experience designing and running evals for non-deterministic systems</li> <li>Strong software engineering fundamentals — TypeScript/Python, modern web stack, API design</li> <li>Pragmatic judgment about when to use agents, when to use simpler pipelines, and when not to use AI at all</li></p><p></p>