RL Environments Engineer
Bespoke Labs· RL Environments
Mountain View$250k - $300kFull-timePosted 1mo ago
About the role
Delivery-focused engineering role building pipelines to mass-produce RL environments and agentic coding tasks. Responsible for designing high-fidelity coding worlds, automating task generation at scale, and maintaining quality and verification as volume increases.
Responsibilities
- Build environment-generation pipelines. Own systems that produce RL environments programmatically, including templating, automated grading, verification, and QA.
- Create complex coding worlds around real codebases with their conventions, dependencies, tooling, and technical debt.
- Scale agentic task creation to thousands with automation handling heavy lifting.
- Build tools that raise throughput and remove bottlenecks in environment production.
- Own the full task lifecycle: prompt, environment, grader, frontier-model evaluation, failure analysis, and iteration until tasks are rigorous, fair, and hard to game.
- Defend quality at scale by catching reward hacking and grader loopholes and building verification and standards.
- Direct frontier coding agents to build and validate environments, judging their outputs and catching subtle failures.
Qualifications
- Shipped volume of agentic coding tasks or environments; demonstrated ability to drive quantity and cost of production
- Experience scaling output via automation rather than purely increasing headcount
- Strong software engineering fundamentals with production-ready fluency across several languages
- Experience with production software: large codebases, build systems, testing, deployment, on-call, root cause analysis
- Adversarial mindset about graders and model cheats; ability to fix vulnerabilities
- Clear understanding of frontier coding agents capabilities and limitations
- Ownership mindset: capable of building, debugging, and shipping with minimal supervision
Skills
Required:Shipped production volume of agentic tasks/environmentsAutomation and pipelines for task generationSoftware engineering fundamentals
Benefits
- Health, dental, and vision coverage
- 401(k)
- Daily onsite lunch provided
- Visa sponsorship and relocation support available
- Direct impact on how the industry trains and evaluates agents
Last updated Oct 4, 2026. Interested? Apply on the company site.
About Bespoke Labs
Bespoke Labs: Ship Reliable AI Agents with SOTA Data Curation
Bespoke Labs optimizes AI agents using cutting-edge research on data curation and evolutionary algorithms. Trusted by Fortune 500 enterprises and frontier labs.
Environment Research LabRL environmentsRobust AI agentsagent revolutionbessemer-ai-infrastructure-2026data curationinfrastructureproduction environments
More open roles at Bespoke Labs
- MTS, Post-Training (Enterprise)3w agoMountain View, Remote · Engineering & Research
- Fulfillment Operations Associate4w agoRemote · Operations
- Founding Recruiter3mo agoMountain View · Engineering & Research