About the role

What you’ll do

• Lead design and delivery of reliable, secure, scalable AI/ML systems
• Own AI architecture, model development, and optimization
• Drive system integration across cross-functional teams
• Set engineering standards for production LLM systems
• Provide technical leadership on agentic AI and RAG solutions
• Ensure evaluation rigor and observability in production

What you’ll need

• 6+ years software engineering with production GenAI/LLM systems
• Hands-on agentic AI: reasoning loops, tool calling, multi-agent orchestration
• Practical RAG expertise: chunking, embeddings, vector DBs, re-ranking
• LLM evaluation/observability experience: golden datasets, LLM-as-judge, RAGAS, LangFuse/LangSmith
• Strong prompt engineering and production system prompt design
• AWS GenAI stack, Python/Node.js, Docker, reliability patterns, and Bedrock Agent Core

Original job description