Research Engineer, RL Env

What you'll do

• Define and implement environment tasks, observations, actions, state transitions, rewards, and scoring.
• Train and compare baseline agents through controlled experiments; make evaluations reliable and investigate failures.
• Collaborate with domain experts and engineers to develop reusable environments, evaluation tools, and documented methods.

What they ask for

• Hands-on experience formulating RL problems, constructing environments, training agents, and critically assessing results.
• Strong programming and software debugging skills.
• Sound experimental design and statistical reasoning, including evaluation splits and variability.
• Ability to reason about environment dynamics, reward design, and agent behavior, and trace unexpected results to concrete causes.

Nice to have

• Experience building interactive environments, simulators, or benchmarks used by other researchers.
• Work on agent evaluation, reward design, imitation learning, or learning from real-world data.

Pay

$170K – $300K USD base salary

AI focus

Develop reinforcement learning environments and experiments for training and evaluating models; test whether measured progress reflects useful behavior.