Senior Software Engineer

You'll design, build, and refine RL tasks, owning the full lifecycle from ideation through grading, failure analysis, and iteration. At this level, we expect you to work on our most complex tasks: environments involving multi-step workflows, realistic stakeholder interactions, large codebases with real conventions and technical debt, or challenging system design problems.

You will use coding agents heavily, and a large part of the job is directing them well, evaluating their output, and knowing when they are failing in subtle ways. You will also contribute to shared infrastructure and tooling, and may take on mentorship responsibilities for newer team members.

What makes someone good at this

Deep software engineering experience across multiple domains, combined with a strong intuition for AI model behavior. You need to anticipate where a model will take shortcuts, distinguish genuine capability gaps from grader issues, and design tasks that target deeper, more subtle failure modes from areas you know well: infrastructure, distributed systems, performance, security, or other specializations.