AI Platform Engineer

What you'll build:

• Agent runtimes and execution loops (plan, act, observe, reflect, retries, stop conditions)
• Agentic loops that convert outcomes into system-level improvements
• Tooling and skills (MCP integration, internal APIs, credentials, sandboxes)

What success looks like in 12 months:

• A managed agent platform that product can rely on for customer-facing delivery
• Agent workflows with high repeatability and clear quality gates
• Engineers spending more time improving the factory and less time in review loops

Who this role is not for:

• If you want to spend most of your time building features directly
• If you haven't shipped production software and lack taste to judge agent output
• If you prefer stable scope and minimal ambiguity