Code RL Research Engineer — AI Coding & RL Systems

Anthropic; San Francisco (CA); Hybrid; USD 500,000 - 850,000; Full time

Job summary

Anthropic is seeking a Research Engineer for the Code RL team in San Francisco. This role involves designing RL environments, running training experiments, and improving model training pipelines. Candidates should have strong software engineering skills, deep Python expertise, and a commitment to building safe AI systems.

The ideal candidate will balance research exploration with engineering implementation, ensuring high code quality and performance. Salary range is between $500,000 to $850,000 annually.

Qualifications

• Strong software-engineering skills and deep Python expertise, including async and concurrent programming.
• Experience with reinforcement learning, RLHF, post-training, or LLM finetuning.
• Experience with large-scale distributed training and performance profiling.

Responsibilities

• Design RL environments and coding tasks, and build reward signals.
• Run training experiments on frontier models and diagnose model behavior.
• Improve speed and reliability of training pipelines.

Skills

Software engineering skills

Deep Python expertise

Debugging across the stack

Research exploration and engineering implementation

Education

Bachelor’s degree or equivalent

Tools

PyTorch

CUDA/GPU or TPU

Job description

Anthropic is seeking a Research Engineer for the Code RL team in San Francisco. This role involves designing RL environments, running training experiments, and improving model training pipelines. Candidates should have strong software engineering skills, deep Python expertise, and a commitment to building safe AI systems.

The ideal candidate will balance research exploration with engineering implementation, ensuring high code quality and performance. Salary range is between $500,000 to $850,000 annually.