RL Environment Engineer

The role

You will design and build production-grade RL environments grounded in real enterprise workflows. You will work with researchers to create reward functions, evaluation environments, and task suites to improve model capabilities.

What you will do

• Design and build production-grade RL environments from task spec to versioned release
• Write reward functions and programmatic verifiers
• Build high-fidelity evaluation environments with seeded failure modes
• Build reliable model and agent harnesses with bounded behaviour and explicit output verification
• Work with frontier lab researchers to design task suites
• Measure task difficulty and solvability by running frontier models against environments
• Ship quickly and help set standards for building tasks and environments

Required qualifications

• 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 goals from researchers into well-scoped, working systems
• A high-ownership, action-oriented mindset
• Startup experience
• Clear written and verbal 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 roles
• Experience with sensitive enterprise data or other high-trust production systems
• Previously a founder or early employee at a startup

Benefits

• 100% covered medical, dental, and vision
• Unlimited PTO
• Free gym + workout class memberships (via Wellhub)
• $500 desk allowance
• Up to $15,000 relocation bonus where applicable

Before you apply

• Intro Chat (20 min)
• Technical Screen (45 min) including technical discussion and systems design challenge
• Take-home project (4 hours)
• Onsite (~3 hrs)
• References

About the company

Replay helps businesses monetize their historical operating data by licensing it to frontier AI and data labs for model training. They are building the first-ever bank for enterprise data.