Tech and design

Research Engineer, Code RL (Reinforcement Learning)

AnthropicNew York City, NY

• Pay$500,000–850,000 per year
• WhereNew York City, NY
• Skills and toolsPython, Async programming, Concurrent programming, Reinforcement learning, RLHF, LLM finetuning, PyTorch, Distributed training, CUDA, Code verification
• You’ll needBachelor's degree or equivalent
• AlsoOffice at least 25%
• ReferenceRef. 6252
• In the paper untilThu 19 Nov

About the job

Hybrid, office at least 25%. Develop reinforcement-learning systems to train models to write, test, debug, and ship software. Strong Python skills, including async and concurrent programming. Bachelor’s degree or equivalent.

This is our short summary. Read the full posting on boards.greenhouse.io.

Found on boards.greenhouse.io. Not placed by the employer; applications go to the original posting.