Find your next role
Discover roles across ambitious teams
1,848 jobs
- More jobs
Replay
Rl Environment Engineer
New York, NY · On-site · Full time · Mid level
$220k–$320k / year
About the role
Build production-grade RL environments using real enterprise data to improve AI training datasets. Collaborate with frontier AI labs to design and tune realistic, verifiable environments.
What you’ll do
• Design and build production-grade RL environments. • Write reward functions and programmatic verifiers. • Build evaluation environments with seeded failure modes. • Turn de-identified data into realistic agent contexts. • Work with researchers to design task suites.
What you’ll bring
• 3-5+ years ML/software engineering experience. • Built production-grade RL environments used in training. • Ability to scope ambiguous goals into working systems. • Experience with environment design tradeoffs. • Strong communication with technical and non-technical partners.
Life at Replay
Offers $220-320K salary, equity, full medical coverage, unlimited PTO, gym memberships, desk allowance, relocation bonus.
About Replay
Replay helps businesses unlock new revenue streams by providing valuable proprietary data for frontier AI model training.