Senior RL Environment Engineer — Real-World Data Systems

Replay; New York (NY); On-site; USD 220,000 - 320,000; Full time

Benefits offered by this job

Base salary $220–320K

Equity

Medical, dental, and vision insurance

Unlimited PTO

Gym memberships

Desk allowance

Relocation bonus up to $15,000

Job summary

Replay is hiring an RL Environment Engineer to turn real enterprise data into realistic, verifiable training environments for frontier AI labs. You will own production-grade RL environments and work directly with researchers to understand capability gaps and design task suites that expose and train against them.

The role emphasizes high ownership, collaboration with frontier researchers, and shipping robust environments that scale with the business.

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 researchers' goals into well-scoped, working systems.
• Understanding environment design tradeoffs: task spec, state design, determinism, solvability.

Responsibilities

• Design and build production-grade RL environments grounded in real enterprise workflows.
• Write reward functions and verifiers that score outcomes reliably and resist shortcuts.
• Create high-fidelity evaluation environments with seeded failure modes and reliable harnesses.
• Transform Replay's de-identified data into realistic state, tools, and context for agents; keep environments reproducible and safe.
• Collaborate with frontier lab researchers to identify capability gaps and design task suites to train against them.
• Measure task difficulty and solvability by testing frontier models against environments and tuning for usable training signals.
• Ship quickly and establish standards for how Replay builds tasks and environments.

Skills

ML/Software engineering

Production RL environments

Research collaboration

Ambiguity to working systems

Tools

RL Environments

Experimentation

Job description

Replay is hiring an RL Environment Engineer to turn real enterprise data into realistic, verifiable training environments for frontier AI labs. You will own production-grade RL environments and work directly with researchers to understand capability gaps and design task suites that expose and train against them.

The role emphasizes high ownership, collaboration with frontier researchers, and shipping robust environments that scale with the business.