Senior Manager AI Software Engineer

About the job Established in 2004, Dubai Holding is a global investment company with investments in more than 34 countries and a combined workforce of nearly 45,000 individuals. In line with the vision of Dubai’s leadership and economic diversification strategy, Dubai Holding companies have nurtured sectors, irrevocably transforming Dubai’s socio-economic landscape and positioning Dubai as a diversified, globally integrated economy. Dubai Holding is committed to the diversification of Dubai’s non-oil economy. Our portfolio, valued at over AED 284+ billion, spans 10 sectors, including real estate, hospitality, leisure & entertainment, ICT, design, education, media, retail, manufacturing & logistics, and science. For the Good of Tomorrow Dubai Holding is looking to hire a Senior Manager AI Software Engineering at the corporate office, reporting to the Associate Director Software Engineering. The job holder is responsible for designing, building, and operating production-grade AI agents on Microsoft Foundry — LLM-powered systems that reason, use tools, and orchestrate multi-step workflows against enterprise data and services. This is a hands-on, pro-code role: the engineer writes Python, integrates Azure services, and ships agentic applications that drive measurable business impact. The engineer works within agile teams alongside Product, Data Science, and Architecture to take agent use cases from prototype to production. Key Responsibilities: AI Agent Development on Microsoft Foundry • Design, build, and deploy pro-code AI agents on Microsoft Foundry, leveraging its agent framework, model catalogue, and tool/function-calling capabilities. • Integrate agents with Palantir Foundry via MCP (Model Context Protocol) to fetch enterprise data and execute Ontology actions, alongside other tool, retrieval, memory, and multi-agent orchestration patterns in Python. • Build evaluation harnesses and guardrails (groundedness, safety, cost, latency) and iterate on prompts, tools, and architectures based on measured outcomes. LLM Engineering & Productionization • Apply prompt engineering, structured output, RAG, and grounding techniques appropriate to each use case. • Operate agents in production: observability, tracing, cost monitoring, regression testing, and incident response. • Manage versioning of prompts, tools, and agent configurations alongside code. Azure & Platform Integration • Integrate with Azure services (Azure OpenAI, AI Search, Storage, Functions, Container Apps, Key Vault, Entra ID) to deliver secure, scalable agent solutions. • Build and maintain CI/CD pipelines for agent deployment, including automated evals as a release gate. • Implement authentication, authorization, secret management, and data-handling patterns aligned with enterprise security standards. Cross-functional Collaboration • Work closely with Product Managers, Data Scientists, and IT Architects to translate agent use cases into delivery plans. • Communicate trade-offs (model choice, latency, cost, accuracy) clearly to technical and non-technical stakeholders. • Champion agentic patterns and reusable components across the engineering organization. Who we are looking for: Software engineering experience with 2+ years of hands-on experience building AI agents and production-grade LLM-based/agentic systems, including tool use, orchestration, RAG, evaluations (evals), and multi-agent workflows. Education / Professional Certifications: • Bachelor’s degree in computer science, Engineering, or related quantitative field • Advanced degrees preferred. Technical Competencies: • Strong Python — idiomatic, typed, tested; comfortable with async and modern packaging • Proven experience building production AI agents in code (e.g. Microsoft Foundry / Azure AI Foundry, Semantic Kernel, AutoGen, LangGraph, LlamaIndex, OpenAI Agents SDK, or equivalent custom frameworks) • Microsoft Foundry experience strongly preferred (agent authoring, model catalog, connectors, deployment) • Azure exposure — Azure OpenAI, AI Search, identity, storage, serverless compute; familiarity with Azure DevOps or GitHub Actions • Deep working knowledge of LLM application patterns: tool/function calling, structured outputs, RAG, memory, multi-agent orchestration • Experience with evaluation frameworks and observability for LLM systems (tracing, prompt/response logging, automated evals) • DevOps fundamentals: Git, CI/CD, containers, infrastructure-as-code; exposure to data engineering and vector stores is a plus Behavioural Competencies • High-energy, ownership-driven mindset • Strong problem-solving and analytical skills • Excellent communication and collaboration abilities • Comfortable navigating ambiguity and driving clarity • Experience in agile/start-up environments preferred • Track record of taking AI/ML or agent projects from prototype to production As much as we would be delighted to entertain all applicants, due to the high volumes of applications, only successful applicants will be contacted within 14 business days. This job description is not all inclusive. Dubai Holding reserves the right to amend this job description at any time. Dubai Holding is an Equal Opportunity Employer, committed to a diverse and inclusive work environment.

Bachelor’s degree in computer science, Engineering, or related quantitative field. Advanced degrees preferred. 2+ years of hands-on experience building AI agents and production-grade LLM-based/agentic systems, including tool use, orchestration, RAG, evaluations (evals), and multi-agent workflows. Strong Python skills (idiomatic, typed, tested), async and modern packaging. Proven experience building production AI agents in code (e.g. Microsoft Foundry / Azure AI Foundry, Semantic Kernel, AutoGen, LangGraph, LlamaIndex, OpenAI Agents SDK, or equivalent frameworks). Microsoft Foundry experience strongly preferred. Azure exposure (Azure OpenAI, AI Search, identity, storage, serverless compute); familiarity with Azure DevOps or GitHub Actions. Deep knowledge of LLM application patterns: tool/function calling, structured outputs, RAG, memory, multi-agent orchestration. Experience with evaluation frameworks and observability for LLM systems (tracing, prompt/response logging, automated evals). DevOps fundamentals: Git, CI/CD, containers, infrastructure-as-code; exposure to data engineering and vector stores is a plus.

Design, build, and deploy pro-code AI agents on Microsoft Foundry; integrate agents with Palantir Foundry via MCP to fetch enterprise data and execute Ontology actions; build evaluation harnesses and guardrails (groundedness, safety, cost, latency); apply prompt engineering, structured output, RAG, and grounding; operate agents in production (observability, tracing, cost monitoring, regression testing, incident response); manage versioning of prompts, tools, and agent configurations; integrate with Azure services to deliver secure, scalable agent solutions; build and maintain CI/CD pipelines for agent deployment with automated evaluations as a release gate; implement authentication, authorization, secret management, and data-handling patterns; collaborate with Product Managers, Data Scientists, and IT Architects to translate use cases into plans; communicate trade-offs to stakeholders; champion reusable components across the engineering organization.