Software Engineer – Full Stack AI (US-Remote)

Integrate LLM APIs (OpenAI, Anthropic, AWS Bedrock) into production features; build RAG systems, vector search, and embedding pipelines; optimize latency, inference cost, and hallucination guardrails; establish evaluation/observability and PHI-handling constraints. 5+ years SWE with strong Python backend, production LLM/RAG/vector-DB experience, AWS cloud-native, regulated-environment experience. Explicitly a builder (not research) role.