Staff Software Engineer II (AI Platform Engineer)

This is a hands-on, technical leadership role responsible for architecting and building the Agentic AI Platform to support multi-agent orchestration and retrieval-augmented generation (RAG) within enterprise microservices.
Design scalable backend systems using Java (Spring Boot) and Python (FastAPI/Flask), and expose robust RESTful and gRPC APIs that connect services, AI agents, and front-end clients.
Integrate LLMs (GPT, Claude, Mistral, Gemini) and optimize RAG pipelines with vector databases (Pinecone, Weaviate, FAISS) using LangChain, LangGraph, or Autogen.
Lead the design of distributed, fault-tolerant architectures with auto-scaling, monitoring, and observability via Kubernetes, Docker, Prometheus, and Grafana.
Partner with senior engineers and product leads to define the platform roadmap; mentor developers, set coding standards, and lead design reviews with a bias for action.
Explore new frameworks and deployment models to advance production GenAI capabilities, drive automation, and open-source adoption; hybrid work arrangement with limited travel.