RL Environment Engineer (Full-time, Part-time, or Contract)

Besimple AI is building training systems for conversational agents. The RL Environment Engineer will create reinforcement learning environments, rewards, simulators, and evaluation tools that help voice agents learn to complete real-world tasks reliably.

Responsibilities:

• Define tasks, observations, actions, state transitions, rewards, and termination conditions. Create environments where agents ask questions, use tools, recover from errors, and reach verifiable outcomes
• Implement checks for task completion and intermediate progress. Find reward-hacking opportunities, ambiguous success criteria, and shortcuts that let agents pass without solving the task
• Work with recorded conversations and human demonstrations to construct scenarios, starting states, alternative continuations, and realistic failure cases
• Develop user and tool simulators that respond to an agent’s actions, maintain consistent state, and support varied, repeatable interactions
• Build rollout interfaces, parallel execution, logging, replay, and debugging tools. Make failures reproducible and environments easy to connect to training pipelines
• Work with researchers to run baseline policies and training experiments, measure learning progress, and test whether improvements transfer to unfamiliar scenarios

Requirements:

• Experience building RL environments is the core requirement
• We're looking for an engineer with experience building reinforcement learning environments
• Hands-on experience building or substantially extending environments used to train or evaluate RL agents
• Strong engineering skills and experience writing tested, maintainable software
• Experience defining task interfaces, managing environment state, implementing rewards, and debugging agent–environment interactions
• The ability to investigate why an agent fails—or succeeds for the wrong reason—and improve the environment accordingly
• Clear technical communication and comfort taking an open-ended problem from an initial prototype to a reliable system
• We welcome recent graduates with substantial academic or open-source projects, as well as engineers with industry experience
• US citizen/visa only
• Speech experience is a plus
• Speech, audio, conversational agents, or full-duplex interaction
• Tool-use, coding, browser, or computer-use environments
• User simulators, executable rewards, reward models, or preference data
• Gymnasium-style interfaces, distributed rollouts, or integration with RL training frameworks
• Using human demonstrations or real-world interaction data to construct training tasks
• Reproducible evaluation, deterministic replay, and testing for reward hacking