Deep hands-on expertise in several of the following: LLM platforms, model serving, inference optimization, AI gateways, model routing, RAG, embeddings/vector search, agent frameworks, tool execution, AI orchestration, LLMOps/MLOps, evaluation systems, AI observability, or AI security controls.\. The role solves complex AI platform engineering problems and drives reusable, secure, reliable, observable, and cost-efficient capabilities that enable teams to deliver enterprise AI and GenAI solutions at scale.