Staff AI Platform Engineer

We are hiring a Staff AI Platform Engineer to build and scale an enterprise AI/LLM platform focused on agent orchestration, model gateways, RAG, evaluation, safety, and observability.

Responsibilities:

• Build agent/workflow orchestration with state management, retries, fallbacks, and HITL approvals.
• Develop LLM/model gateways with routing, rate limits, quotas, policies, telemetry, and OpenAI integrations.
• Build RAG and retrieval systems using hybrid search, vector databases, RBAC, citations, and provenance.
• Develop AI evaluation and safety frameworks, including regression testing, quality gates, and drift monitoring.
• Implement end-to-end observability and tracing across agents, tools, retrieval, and models.
• Design reliable, scalable AI infrastructure for regulated enterprise environments.

Requirements:

• 8+ years of software/platform engineering experience.
• Strong Python/Java/Go/TypeScript experience.
• Hands-on experience with LLMs, Agentic AI, RAG, vector search, and AI platforms.
• Strong knowledge of distributed systems, APIs, microservices, Kubernetes, and cloud.
• Experience with LLM frameworks such as LangGraph/LangChain and observability tools is a plus.