Staff AI Engineer — Agent Platform (all genders)

<p>wingmaite captures the knowledge companies never write down: who decides what, how work actually gets done, and why decisions were made. Our AI agents use that knowledge to answer questions and get work done.</p><p>We're looking for a Staff engineer to own the technical quality and direction of our agent platform. You'll build features end to end, from the agent into the backend. You won't manage people. You'll work closely with our CTO as a technical sparring partner.</p><h3>What You'll Do</h3><ul><li><p><strong>Design the agents:</strong> Decide how our agents plan, use tools and handle multi-step work, and where people need to step in. Build reusable components so each new use case doesn't need its own system.</p></li><li><p><strong>Connect agents to company knowledge:</strong> Build how that knowledge reaches the agents, together with the people who decide what it should contain.</p></li><li><p><strong>Make answers reliable:</strong> Agents should be correct, cite their sources, show people only what they're allowed to see, and know when not to act.</p></li><li><p><strong>Track quality:</strong> Build evals, monitor quality and cost, and keep our model choices up to date.</p></li><li><p><strong>Ship end to end:</strong> Build features from the agent through to the backend yourself.</p></li><li><p><strong>Keep the architecture consistent:</strong> Set the patterns others build on, document decisions, keep specs current, and review designs with engineering, product and design.</p></li></ul><h3>How We Work</h3><p>We build features as one team: design, product, engineering and AI together, from the first idea to production. You'll help shape a feature while it's still a problem and stay with it until it works for users. Agents depend on the knowledge behind them, so we build both as one system. We write decisions down and discuss disagreements openly.</p><h3>What This Role Is Not</h3><p>A management role, a prompt-engineering role, or an infrastructure or security role.</p><h3>What We're Looking For</h3><p><strong>Must-Haves</strong></p><ul><li><p>You've shipped multi-step, tool-using LLM agents to production (LangGraph or similar)</p></li><li><p>You know when sub-agents help, how to build good evals, and why retrieval fails</p></li><li><p>Fluent in <strong>Python</strong> and productive in <strong>TypeScript/Node</strong> (NestJS is a plus)</p></li><li><p><strong>PostgreSQL</strong> and data modeling</p></li><li><p>You use AI coding tools such as Claude Code every day</p></li><li><p>You write clear specs and can explain trade-offs to people who aren't engineers</p></li><li><p>Fluent English (C1–C2)</p></li></ul><p></p><p><strong>Nice-to-Haves</strong></p><p>None of these are required, but they'll help you get up to speed faster:</p><ul><li><p>You've connected agents to tools and data through <strong>MCP</strong></p></li><li><p>You've worked with <strong>knowledge graphs</strong> or other ways of modeling how people, work and information relate</p></li><li><p>You've run models in production on <strong>AWS Bedrock or Vertex AI</strong></p></li><li><p>You've traced and debugged agents with <strong>LLM observability</strong> tools such as Langfuse</p></li><li><p>You s