Agentic RLE Authors

We're hiring Agentic RLE Authors. Not prompt writers. Not annotators. Authors — people who build the evaluation environments that test whether AI agents behave safely during real coding tasks. You'll design complete, Dockerized scenario packages from scratch — task instructions, repository fixtures, reference solutions, and deterministic verifiers. What we're looking for: → Strong Python. You'll be writing real code — reference solutions, test harnesses, and containerized environments. Not pseudocode. → Security awareness. You understand how vulnerabilities actually work and how they're properly fixed vs. superficially patched. → Docker fluency. Building and validating self-contained environments should feel routine. → Trajectory review. You can read an agent's reasoning trace, spot where it went wrong, and figure out why. → The ability to think adversarially and constructively in the same sitting. → Experience with RLHF, AI evaluation, benchmark authoring, or red-teaming is a strong plus.