RL Environments Engineer

About Bespoke LabsBespoke Labs is an applied AI research lab pioneering data and RL environment curation for training and evaluating agents.Recently, we curated Open Thoughts, one of the best open reasoning datasets used by multiple frontier labs, trained SOTA specialized models such as Bespoke-MiniChart-7B and Bespoke-MiniCheck, and taught agents to do multi-turn tool-calling with reinforcement learning.Bespoke is uniquely positioned to capture a large market share of data and RL environment curation. About the RoleYou will own coding environments end to end. You choose what world to build, design the tasks inside it, build the grading, run frontier models against it, and harden it until the only way to pass is to actually do the work.This is a delivery role. We care most about whether you have done this before and can point to what came out of it. If you have built agentic coding environments or tasks at real volume and can tell us how many and how hard they were, we want to talk. What You'll DoBuild high-fidelity coding worlds around real codebases, with the conventions, dependencies, tooling, and accumulated mess that real software has.Choose which environments are worth building. A strong coding environment hits several marks:Targets work where frontier models measurably struggleExercises real engineering, meaning navigation, diagnosis, sequencing, and design, and not just writing a functionRests on a codebase with enough history and structure that shortcuts do not surviveHas a clear pass condition that a reviewer would agree withProduces many varied tasks from a single world rather than oneDesign tasks across the full lifecycle. Prompt, environment, grader, running frontier models, failure analysis, and iteration, until each task is rigorous, fair, and hard to <game.Build> grading and sandboxed execution that is deterministic and cannot be gamed. Assume the model will try to pass without doing the work, and close the door before it finds it.Remove whatever is slowing the team down. Build the internal tooling that makes everyone around you <faster.Direct> frontier coding agents heavily to build and validate environments, judging their output and catching the quiet failures they produce.What We're Looking ForA record of shipped volume. You have built agentic coding tasks or environments and can show us how many you personally drove and what they cost to produce.Experience scaling that output through automation rather than through more people doing more manual work.Strong software engineering fundamentals and fluency in several languages that holds up in production code.Real experience with production software. Large codebases, build systems, testing, deployment, on-call, and root cause analysis. You know what real engineering work feels like because you have done it.An adversarial mindset. You look at a grader and ask how a model would cheat it, and then you fix that.A clear sense of what frontier coding agents can and cannot do, and where they cut corners.Ownership. You build, debug, and ship without much <supervision.You> May Be a Good Fit If You AlsoHave worked on RL training systems, post-training, verifiers, or tool-use harnessesCome from developer tooling, CI/CD, sandboxes, or code execution infrastructureHave built large-scale automated test generation, fuzzing harnesses, or benchmark suites, which is close cousin work even if it was never called an RL environmentHave contributed to a public agentic benchmark such as Terminal-BenchHave open-source work that other people depend onWhat We OfferLocation: Mountain View, CA (Onsite)Base Salary: $250,000 – $300,000 USD / yearAdditional Comp: 25% performance-based bonus + equityBenefits & PerksHealth, dental, and vision coverage401(k)Daily onsite lunch providedVisa sponsorship and relocation support availableDirect impact on how the industry trains and evaluates agentsWe value different backgrounds and paths into this work. If this role excites you but you do not check every box, apply anyway.