Reviews AI-generated reinforcement learning code and model outputs for correctness. Suits engineers who have built and debugged RL systems themselves and can work flexible remote hours.
About the role
This RL Engineer role pays $100/hour and wants hands-on experience implementing reinforcement learning algorithms like PPO, SAC, DQN, or RLHF, plus real fluency in PyTorch, JAX, or Stable-Baselines3. The evaluation work is reviewing AI-generated RL code and model outputs for correctness at a level that requires having built and debugged RL systems yourself. It's remote and flexible, one of the more technically specific STEM roles Ethos runs.
Official source: agent.askethos.com. Details can change; the platform's page is the final word. Something wrong with this listing? Tell us.
More coding jobsMore AI agent and RL task jobs All Ethos roles How much does Ethos pay? Is Ethos legit? How Ethos screens applicants
