RL Environments Engineer

The role

You will build pipelines to mass-produce RL environments and design complex coding worlds for agents. You will scale agentic task creation and build internal tools to increase throughput.

What you will do

• Build environment-generation pipelines including templating, automated grading, verification, and QA.
• Create complex coding worlds around real codebases.
• Scale agentic task creation to thousands using automation.
• Build internal tooling and infrastructure to raise throughput.
• Own the full task lifecycle from prompt to failure analysis.
• Defend quality at scale by catching reward hacking and grader loopholes.
• Direct frontier coding agents to build and validate environments.

Required qualifications

• A record of shipped volume of agentic coding tasks or environments.
• Experience scaling output through automation.
• Strong software engineering fundamentals and fluency in several languages.
• Real experience with production software including large codebases, build systems, testing, deployment, on-call, and root cause analysis.
• An adversarial mindset.
• A clear sense of what frontier coding agents can and cannot do.
• Ownership to build, debug, and ship without much supervision.

Nice to have

• Worked on RL training systems, post-training, verifiers, or tool-use harnesses
• Come from developer tooling, CI/CD, sandboxes, or code execution infrastructure
• Built large-scale automated test generation, fuzzing harnesses, or benchmark suites
• Contributed to a public agentic benchmark such as Terminal-Bench
• Open-source work that other people depend on

Benefits

• Health, dental, and vision coverage
• 401(k)
• Daily onsite lunch provided
• Visa sponsorship and relocation support available

Before you apply

• Visa sponsorship and relocation support available

About the company

Bespoke Labs is an applied AI research lab pioneering data and RL environment curation for training and evaluating agents.