AI Agent Engineer

We are looking to hire an AI Agent Engineer who will be responsible for designing, building, and operating AI agent systems using Microsoft Foundry for a client based in the Dubai, which is one of the largest companies in the region.This position is a contract role with an initial duration of 12 months and is renewable based on performance. The role sits within the IT Department and reports directly to the Associate Director Software Engineering.Key responsibilities:Design, build, and deploy production-grade AI agents using Microsoft Foundry, including model catalog, agent framework, and tool/function-calling capabilitiesIntegrate AI agents with enterprise systems (including Palantir Foundry via MCP) to access data and execute ontology-based actionsDevelop retrieval, memory, tool-use, and multi-agent orchestration patterns using PythonBuild evaluation frameworks and guardrails covering groundedness, safety, latency, and cost efficiencyApply LLM engineering techniques such as prompt engineering, structured outputs, RAG, and grounding strategiesOperate AI agents in production including observability, tracing, monitoring, cost optimization, and incident responseManage versioning of prompts, tools, configurations, and agent logic alongside codeIntegrate solutions with Azure services including Azure OpenAI, Azure AI Search, Storage, Functions, Container Apps, Key Vault, and Entra IDBuild CI/CD pipelines with automated evaluation gates for safe and reliable deploymentsEnsure secure design patterns for authentication, authorization, secrets management, and enterprise data handlingCollaborate with Product, Data Science, and Architecture teams to deliver end-to-end AI solutionsPromote reusable agentic frameworks and best practices across engineering teamsKnowledge, skills & experience:Bachelors degree in Computer Science or relevant.Strong hands-on experience in Python.Proven experience building LLM-based or AI agent systems (tool use, orchestration, RAG, evaluation frameworks)Experience with Microsoft Foundry or similar frameworks (Semantic Kernel, AutoGen, LangGraph, LlamaIndex, OpenAI Agents SDK, etc.)Strong understanding of Azure ecosystem (Azure OpenAI, AI Search, Storage, Functions, Entra ID, DevOps tools)Deep knowledge of LLM application patterns.Strong DevOps knowledge including Git, CI/CD, containers, and infrastructure-as-codeExposure to data engineering concepts and vector databases is an advantageStrong problem-solving, communication, and stakeholder management skillsExperience working in agile or fast-paced environments delivering AI/ML products from prototype to productionAvailability:Preference will be given to candidates available immediately or with a maximum 30-day notice period after accepting the offer.We are looking for a candidate who will be able to work in the United Arab Emirates. Please apply with your resume and ensure you provide your contact details.We will review your application within 7 working days. Should your profile fit the requirements of the role, a consultant will be in touch to discuss your experience in more detail and outline the next steps.