AI Lead & Architect: Production-Grade Multi-Agent Systems

Agent Orchestration:
Lang Chain, Lang Graph, CrewAI - not just conceptual tRAG & Vector Stores:
Chroma, Weaviate, Pinecone, know where RAG breaks ePython / Type Script:
Primary languages for agent + backend development Lang Smith / Observability:
Tracing, evaluation, debugging agent run sCloud Platforms:
Azure, AWS, GCP (at least one) - deployment, infra, managed service sMCP / Shared Context:
Model Context Protocol, CLAUDE.md, Bead sAgent Evaluation:
Testing non-deterministic outputs, guardrails, eval sCI/CD & Dev Ops:
Git, containers, pipelines - agents need to ship Client Communication:
Can present architecture to a CXO without jargo Must have

• :
  Deployed 2–3 agent-based systems in production - stateful, multi-step, real use
• rsUsed Lang Graph for multi-agent orchestration with memory, tool routing, and state manageme
• nt Built projects where AI (Claude Code, Codex, Cursor) wrote significant portions of the co
• de Implemented RAG pipelines end-to-end - chunking, embedding, retrieval, re-ranking, evaluati
• on Integrated agents with real enterprise APIs - not just OpenAI playground or sample da
• ta Debugged a production agent failure - and fixed it without blaming the mod
• elCan articulate when NOT to use agents - that is how we know you have built thin