Must-have:Shipped LLM-backed product features to production against real usersComfortable full-stack, with enough backend depth to work in agent orchestrationAutonomy working from an ambiguous specA collaborative mindset with an ability to work across PM, design, and domain expertsWillingness to develop an Applied AI skillset including writing evals, using LLM observability tools, and being thoughtful about qualityNice-to-have:Startup experience, as a founder or as an early engineerA track record of 0→1 projects you took from nothing to something people useExperience working directly with customers, and comfort being in the room when they use what you builtExperience in internal audit, SOX, financial services, accounting, or complianceFamiliarity with our stack: TypeScript, React, GraphQL, Node.js, PostgreSQL, Python, and TemporalExperience with document processing, PDF/Excel manipulation, or evaluation frameworks for model outputNot a fit if:You’re not interested in deeply learning about AgentsYou’ve never built a product to scaleYou need a fully specified ticket to startYou'd rather not be in the room with customers and domain expertsWhat Should Excite You0→1 on the biggest bet: You're building the agent and the product from scratch, on the ground floor of where the company is goingReal audit stakes: Your work directly affects what firms put in front of their clients, and what a reviewer is willing to signCustomer proximity: Design-partner firms and an embedded SOX expert use what you ship within days of it landingHigh trust, high autonomy: You're given ambiguous problems and trusted to define the plan
Deadline:30 Oct 2026