eval harnesses Jobs

You will embed directly with customer teams as the engineer on the ground, owning an outcome and shipping a production-grade AI system. You will become the critical technical feedback loop from the field back to product engineering. The work involves taking messy business workflows and putting production agents on them, picking the use case, standing up the architecture, wiring it into the customer’s auth, data, and tools, and hardening it with evals until the team uses it. Alternatively, you might live in a customer’s repo and delivery system to ship an agent-powered path for a migration, a PR review loop, or an incident-to-fix flow. You will measure what matters, ensure the customer can operate the system, and bring the pattern back as another use case for the company's products. This role requires end-to-end ownership from discovery through launch, iteration, and post-launch support, with responsibility for systems that work in the real world.