Agentic AI Architect (Remote from Poland)

This is a remote position.

• Need to have experience in handling big teams. 
  

• You will lead a small, high-output agentic engineering pod migrating AWS Lambda applications to Azure.
  

• Inspired by OpenAI’s Harness Engineering model, your primary job is not writing code — it is designing the harness: the scaffolding, constraints, and feedback loops that let Claude Code agents to do reliable work. 
  

• You own the claudecodeforge scaffolding, define CLAUDE.md specs, enforce architectural
  

• invariants, and build the CI/CD guard-rails that keep agent-generated code coherent. 
  

• You are a player-coach: 70% building harness, 30% guiding the pod.
  

Requirements

• Own and evolve the claudecodeforge scaffolding — repo structure, CLAUDE.md templates, creating agents, MCP tool configs, and custom slash commands 
  

• Decompose the AWS estate into depth-first migration work-packages with clear acceptance criteria agents can validate 
  

• Enforce architecture mechanically (structural tests, linting rules, dependency-layer checks) rather than through documentation alone 
  

• Run weekly entropy-management sweeps using background Claude Code tasks to maintain codebase coherence 
  

• Mentor engineers on prompt-driven TDD, multi-agent orchestration, and Claude Desktop / Cowork workflows 
  

• Report migration velocity, agent utilisation, and risk to stakeholders You Bring 
  

• 6-8 years software engineering; 2+ years leading delivery teams 
  

• Deep AWS and Azure serverless experience (Lambda → Functions, DynamoDB → Cosmos DB, Step Functions → Durable Functions) 
  

• Hands-on Claude Code, Claude Desktop, and Cowork proficiency 
  

• Track record of building developer tooling, CI/CD pipelines, or platform engineering