RL Environment Engineer

What you'll do

• Design, build, version, and release RL environments, reward functions, verifiers, and evaluation harnesses.
• Collaborate with frontier lab researchers to create task suites targeting capability gaps and measure task difficulty and solvability.
• Harden environments against reward hacking and shortcut solutions, and tune them to provide useful training signals.

What they ask for

• 3-5+ years of ML / software engineering experience shipping production systems.
• Personally built production-grade RL environments used in real training or evaluation.
• Ability to turn ambiguous researcher goals into well-scoped, working systems.
• Startup experience, ownership, adaptability to evolving requirements, and clear communication.

Nice to have

• Background at or working with a frontier AI lab, or in research-adjacent engineering.
• Experience in forward-deployed or customer-facing engineering, sensitive enterprise data, high-trust systems, or as a startup founder or early employee.

Pay

$200K-350K USD base salary

AI focus

Create RL environments, reward functions, verifiers, and evaluations that train and assess frontier AI models against enterprise workflows and targeted capability gaps.