Senior GenAI​/AI Platform Engineer – Microsoft Agent Framework

Senior GenAI / AI Platform Engineer – Microsoft Agent Framework

This role is focused on a critical migration and refactoring of an enterprise-grade RAG platform on Azure AI Services. The core task involves re-platforming the current Semantic Kernel orchestration layer to the Microsoft Agent Framework. The ideal candidate will have hands-on experience in this specific migration, rebuilding the orchestration layer using Python/Django while preserving existing API contracts and deploying the solution on Open Shift.

Responsibilities:

• Refactor the platform's orchestration layer from Semantic Kernel to the Microsoft Agent Framework
• Rebuild the orchestration layer using Python and Django without breaking existing API contracts, RBAC, and permissions
• Re-platform SK Native Plugins, Function Calling, Prompt Templates, Memory/Chat History, and Planners/Agents onto the Agent Framework's model
• Preserve retrieval, reranking, prompt assembly, and citation paths within the Azure AI Services/RAG environment
• Deploy migrated microservices on Open Shift (OCP)
• Implement observability and evaluation using Arize Phoenix and Open Telemetry to confirm quality parity

Requirements:

• Hands-on experience refactoring Semantic Kernel plugins, planners, function calling, and memory to Microsoft Agent Framework agents/workflows
• Strong proficiency in Python / Django
• Experience with Azure AI Services / RAG, including Azure AI Search (hybrid retrieval, semantic ranking) and Azure OpenAI (inference + embeddings)
• Knowledge of Model Context Protocol (MCP) for tool/connector integration
• Experience with Open Shift / containerization for deploying microservices
• Familiarity with Observability & Evaluation tools like Arize Phoenix and Open Telemetry instrumentation
• Proficiency with Git Hub, CI/CD pipelines, and Dev Sec Ops  practices

Desired skills:

• Experience with Redis Enterprise for caching/session state
• Knowledge of Azure APIM for gateway and rate limiting

Migration Context

Knowledge Search is a containerized, enterprise-grade RAG platform on Azure AI Services with a Django/Python, deployed on Open Shift. Semantic Kernel is the current orchestration layer, and the SK → MS Agent Framework migration is a Q3 '26 roadmap item that unblocks Agentic Workflows and the Control Panel. The refactor re-platforms SK Native Plugins, Function Calling, Prompt Templates, Memory/Chat History, and Planners/Agents onto the Agent Framework's agents/workflows model.

Must-Have Skills

• Semantic Kernel + Microsoft Agent Framework — hands-on experience refactoring SK plugins, planners, function calling, and memory to Agent Framework agents/workflows (this is the critical, hardest-to-source skill)
• Python / Django — to rebuild the orchestration layer without breaking existing API contracts, RBAC, and permissions
• Azure AI Services / RAG — Azure AI Search (hybrid retrieval, semantic ranking), Azure OpenAI (inference + embeddings), preserving retrieval, reranking, prompt assembly, and citation paths

High-Priority Skills

• Model Context Protocol (MCP) — for tool/connector integration and the Intelligence Layer channel
• Open Shift / containerization — to deploy migrated microservices on OCP
• Observability & Evaluation — Arize Phoenix + Open Telemetry instrumentation, agent/agentic-system registration, and RAG quality/eval validation to confirm parity
• Git Hub / CI-CD / Dev Sec Ops  — PR-based workflows and vulnerability remediation

Medium-Priority Skills

• Redis Enterprise (caching/session state) and Azure APIM (gateway, rate limiting)

The single most differentiated requirement is combined hands-on Semantic Kernel and Microsoft Agent Framework experience paired with Python/Django, since that is the exact intersection where the refactor happens. The remaining skills (Azure AI Search, RAG, OCP, observability) align with what the team already runs today.