Microsoft AI Engineer

Microsoft AI Engineer - Abu Dhabi - 12 Month Contract

Role: AI Engineer (Microsoft Stack)

Duration: 12 month extendable contract

Location: Abu Dhabi

Salary: AED 18,000 per month + VISA + Healthcare

Our client are looking for a Microsoft AI Engineer who is an expert in "Pro-Code" AI development to lead the architecture and implementation of their customers' enterprise-grade agentic systems.

The ideal candidate lives in the Microsoft AI Platform ecosystem but approaches development with a software engineering mindset prioritizing scalability, security, and complex multi-agent orchestration.

Key Responsibilities

• Architect and develop complex multi-agent systems using the Microsoft Agent Framework (integrating patterns from Semantic Kernel and AutoGen).
• Implement Agent-to-Agent (A2A) communication and Model Context Protocol (MCP) to allow agents to discover and invoke enterprise tools dynamically.
• Build robust RAG (Retrieval-Augmented Generation) pipelines using Azure AI Foundry IQ and Azure AI Search for high-accuracy, multi-hop reasoning
• Design hybrid orchestration models: combining Agentic Reasoning (dynamic) with Workflow Orchestration(deterministic business logic).
• Deploy and manage the Foundry Citadel Platform to ensure unified governance, cost control, and observability across all AI workloads.
• Utilize Citadel’s Agent-Level Tracing and automated evaluations to monitor performance and compliance in real-time.
• Develop custom, responsive user interfaces using React or Streamlit that allow humans to interact with, supervise, and steer AI agents.
• Integrate agentic workflows into existing surfaces like Microsoft Teams, custom web portals, or the VS Code AI Toolkit.

Must Have Skills

• Azure AI Foundry (Studio/Hub), Azure OpenAI Service.
• Advanced Python (FastAPI/Pydantic) and/or C# (.NET 8+).
• Microsoft Agent Framework, Semantic Kernel, or AutoGen
• Foundry IQ, Azure AI Search (Vector/Hybrid), Cosmos DB
• Citadel (Foundry Citadel Platform), Microsoft Purview, or AI Content Safety is preferred.
• React.js, Tailwind CSS, and experience with streaming LLM responses.