AI Platform Engineer

Key Responsibilities

• Design, build, and maintain backend services using Python/FastAPI or equivalent that integrate with multiple upstream AI/chat systems via REST APIs.
• Build and tune retrieval pipelines on Azure AI Search, including indexing strategies, chunking, embeddings, hybrid/semantic search, and relevance evaluation.
• Design, configure, and evaluate AI agents using Microsoft's Azure AI Foundry Agent Service or equivalent LLM agent/orchestration frameworks, including grounding agents in enterprise knowledge sources with citations.
• Set up and manage supporting Azure infrastructure, including Blob Storage data pipelines, API Management as an AI/API gateway, managed identities and RBAC, and Log Analytics for usage/cost monitoring.
• Evaluate new platform capabilities pragmatically by distinguishing GA vs. preview features, weighing production-readiness and support/SLA implications before recommending adoption, and communicating those tradeoffs clearly to stakeholders.
• Own end-to-end quality by testing retrieval accuracy on realistic query patterns, including multi-part/comparison-style questions across a large content catalog.
• Write clear technical documentation of architecture decisions and integration contracts for other engineers and non-technical stakeholders.