Founding Agentic Engineer

ABOUT THE ROLE A well-funded flexible-work / gig-economy platform — operating at the intersection of staffing technology and agentic AI — is looking for a Founding Agentic Engineer to own the agent layer end-to-end. You'll work directly with the CTO as one of the earliest engineers shaping how production-grade AI agents are built, measured, and evolved at scale. This is an implementation-focused role: real agents, real consequences, real production systems. The company has raised early-stage funding, operates a live marketplace connecting businesses with flexible-workforce professionals, and is now investing heavily in agentic infrastructure to automate complex integration workflows across the real economy. Nobody has shipped this kind of system at production scale yet — you'd be among the first. WHAT YOU'LL BUILD - A context and self-learning system — a compounding knowledge base of undocumented systems so that onboarding each new integration client is dramatically faster than the last. - Self-healing workflows — agents that detect failures in production, diagnose root causes, and recover autonomously without human intervention. - A meta-harness — the runtime harness agents run on, plus the layer that lets the team build, evaluate, and ship new agents in days rather than months. WHAT YOU'LL DO - Own the agent layer end-to-end: context systems, self-learning pipelines, evals, the harness, and the meta-harness. - Define and establish the patterns by which every agent at the company gets built, measured, and continuously improved. - Partner directly with founders as a true peer — experiment rapidly and drive outcomes independently. - Help build the team: contribute to hiring and grow into leading the engineers who own agentic systems as the company scales. WHAT WE'RE LOOKING FOR Required: - Proven track record shipping production-grade software in fast-moving environments (implementation engineering focus, not purely research). - Strong TypeScript development experience with production-ready code and tooling (familiarity with Effect-TS a plus). - Hands-on experience with PostgreSQL or another relational database in production systems. - Experience with LLMs, agent-based architectures, or agent frameworks — including building and/or evaluating agents. - Experience with evaluation-driven development (evals), self-learning systems, and measuring agent performance in production. - Ability to own complex system components end-to-end and drive outcomes with minimal oversight. - Willingness to contribute to team-building, including hiring and mentoring as the engineering org grows. - Strong collaboration skills; comfortable working directly with founders and cross-functional stakeholders. Nice to Have: - Prior experience at a high-velocity startup or a large-scale engineering organization (e.g., Amazon, GitHub, or similar). - Familiarity with staffing, logistics, or marketplace platform tech stacks. COMPENSATION & BENEFITS - Salary: $150,000 – $300,000 USD annually - Visa sponsorship is available for eligible candidates. LOCATION This is an on-site role based in San Francisco, CA. Candidates must be able to work from the San Francisco office. Visa sponsorship is available.