AI Lead/Architect

Technical Skills Required

Agent Orchestration: LangChain, LangGraph, CrewAI - not just conceptual

Agentic Coding Tools: Claude Code CLI, Cursor, OpenAI Codex, Copilo

tRAG & Vector Stores: Chroma, Weaviate, Pinecone, know where RAG breaks

LLM APIs & SDKs: Anthropic, OpenAI, Gemini - prompt design, tool us

ePython / TypeScript: Primary languages for agent + backend development

LangSmith / Observability: Tracing, evaluation, debugging agent run

sCloud Platforms: Azure, AWS, GCP (at least one) - deployment, infra, managed service

sAPI & System Integration: REST, gRPC, Kafka - enterprise integration pattern

sMCP / Shared Context: Model Context Protocol, CLAUDE.md, Bead

sAgent Evaluation: Testing non-deterministic outputs, guardrails, eval

sCI/CD & DevOps: Git, containers, pipelines - agents need to ship

Client Communication: Can present architecture to a CXO without jargo

n
Must have

• : Deployed 2–3 agent-based systems in production - stateful, multi-step, real use
• rsUsed LangGraph for multi-agent orchestration with memory, tool routing, and state manageme
• ntBuilt projects where AI (Claude Code, Codex, Cursor) wrote significant portions of the co
• deImplemented RAG pipelines end-to-end - chunking, embedding, retrieval, re-ranking, evaluati
• onIntegrated agents with real enterprise APIs - not just OpenAI playground or sample da
• taDebugged 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