AI Engineer - Microsoft Foundry & LLM Solutions

The opportunity

Build and deploy production AI features; search, personalization, content generation, and internal copilots on Microsoft Foundry (Azure AI Foundry) Implement LLM and RAG solutions grounded in governed One Lake data, using the Model Context Protocol (MCP) to connect models to data and tools Develop and tune prompts, retrieval strategies, and agent workflows via the Foundry Agent Service and model catalog Establish deployment, monitoring, evaluation, and cost-management practices around AI projects — recognizing AI products require continual refinement, not set-and-forget delivery Implement CI/CD for AI artifacts, prompt/model versioning, and automated evaluation Partner with data engineering to keep Fabric/One Lake data AI-ready Implement guardrails, prompt-injection defenses, output validation, and PII handling Ensure technical controls stay aligned with Richemont’s requirements and policies Document responsible-AI practices and model evaluations Work under AI Engineering Manager and partner with data science and data engineering on shared infrastructure Mentor junior engineers and contribute to the AI/ML specialization pathway Qualification Microsoft Foundry (Azure AI Foundry) Azure AI and Azure OpenAI Large Language Models (LLMs) Retrieval-Augmented Generation (RAG) Prompt Engineering Model Context Protocol (MCP) Microsoft Fabric and OneLake MLOps and CI/CD Python AI Evaluation and Monitoring Required Microsoft Foundry (Azure AI Foundry) hands-on experience with the model catalog, Foundry Agent Service, evaluation, and deployment Azure AI production experience with Azure AI services / Azure OpenAI and LLM/RAG architectures MCP, RAG & LLMs demonstrated experience with the Model Context Protocol (MCP), retrieval-augmented generation, and prompt engineering Microsoft Fabric & One Lake experience grounding AI on governed Fabric/One Lake data (Lakehouse, Direct Lake, shortcuts) MLOps CI/CD, monitoring, evaluation, and cost management; strong Python 5+ years in ML/AI engineering, with production generative-AI delivery (RAG, copilots, search, or personalization) Experience with MCP, RAG, and LLM integration; strong prompt-engineering skills Familiarity with Microsoft Fabric / One Lake and governed data foundations Strong Python; solid MLOps and software-engineering fundamentals