You'll work across the whole stack: a single feature might run from a Drizzle schema change, through a Hono endpoint, to a new React screen. The agentic toolchain is how you cover that ground – but the judgment to review, verify, and take responsibility for what the tools produce is what makes it work.
What you'll work on
Full, thin vertical slices – backend to frontend – shipped behind previews and a merge queue.
Extending and hardening our agentic-dev toolchain: skills, workflows, and MCP servers the whole team relies on.
Whatever's highest-leverage that week – you'll move across the codebase more than most.
Demonstrated, shippable output built with agentic tools. A portfolio, GitHub, or side projects that actually work – this counts more than any credential.
Deep, hands-on control of at least one agentic coding tool: you write your own skills and commands, build MCP servers, orchestrate multi-agent work, engineer context deliberately, and know precisely when to trust the model and when to verify.
The judgment to review AI-generated code critically. You catch the subtle bug the model slipped in, and you can explain why it's wrong – you don't merge what you can't stand behind.
Solid fundamentals and real debugging chops. When the agent gets stuck, you don't.
Curiosity across the stack. You're comfortable being full-stack precisely because these tools extend your reach.
