RL Environment Engineers: Building Tool Gyms for Knowledge Work

We're hiring an RL environment engineer to help build tool-based environments, commonly known as tool gyms, for knowledge work applications. This paid engagement focuses on creating robust simulation frameworks where models can learn to interact with complex software tools. The resulting environments will directly support advanced reinforcement learning research and training pipelines.

You will spend approximately 20 hours per week developing and testing new tool environments. This involves writing code to simulate various knowledge work tasks, ensuring realistic and stable agent interactions. You will also participate in remote video check-ins to discuss architecture decisions and troubleshoot implementation blockers. Throughout the project, you will iterate on environment designs based on model performance and technical feedback.

We are looking for specialized machine learning professionals with hands-on experience in reinforcement learning environments. We welcome RL engineers, AI researchers, simulation developers, and machine learning infrastructure specialists. Ideal candidates have previously built or maintained custom gyms and are comfortable committing to a part-time weekly schedule.

• Design and implement tool-based environments for knowledge work simulations.
• Write clean and modular code to support reinforcement learning training pipelines.
• Troubleshoot and refine environment mechanics based on testing feedback.
• Collaborate asynchronously and participate in remote progress check-ins.

• Professional experience as a machine learning or reinforcement learning engineer
• Hands-on background building custom RL environments or tool gyms
• Ability to commit to approximately 20 hours of work per week
• Comfortable discussing technical architecture and implementation strategies

• You will be engaged as an independent contractor.
• This is a fully remote opportunity that can be completed on your own schedule.
• Opportunities can be extended, shortened, or concluded early depending on needs and performance.
• Your participation will not involve access to confidential or proprietary information from any employer, client, or institution.
• Payments are processed weekly based on services rendered.
• We are unable to support H1-B or STEM OPT candidates at this time.