Code RL Research Engineer — AI Coding & RL Systems

Anthropic; New York (NY); Hybrid; USD 500,000 - 850,000; Full time

Job summary

Anthropic is hiring a Research Engineer for the Code RL team in New York. Applicants should possess strong software engineering skills and deep expertise in Python to design RL environments and run training experiments. The position requires balancing research and engineering responsibilities while ensuring code quality and performance.

With an annual salary ranging from $500,000 to $850,000, Anthropic aims to build reliable and beneficial AI systems. Candidates must have at least a Bachelor's degree or equivalent experience.

Qualifications

• Have strong software engineering skills and deep Python expertise, including async and concurrent programming.
• Balance research exploration with engineering implementation, and rigorously design experiments and interpret results.
• Experience with reinforcement learning, RLHF, or large-scale distributed training.

Responsibilities

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

Skills

Strong software engineering skills

Deep Python expertise

Research exploration and engineering implementation

Code quality and performance awareness

Education

Bachelor’s degree or equivalent

Tools

PyTorch

CUDA / GPU or TPU

Job description

Anthropic is hiring a Research Engineer for the Code RL team in New York. Applicants should possess strong software engineering skills and deep expertise in Python to design RL environments and run training experiments. The position requires balancing research and engineering responsibilities while ensuring code quality and performance.

With an annual salary ranging from $500,000 to $850,000, Anthropic aims to build reliable and beneficial AI systems. Candidates must have at least a Bachelor's degree or equivalent experience.