Code RL Research Engineer: End-to-End AI Coding

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

Job summary

Anthropic Limited in New York is hiring a Research Engineer for the Code RL team. You will help our models write, edit, test, debug, and ship real software end-to-end, working on real codebases with real tools.

This role blends research and engineering: design RL environments, build reward signals, run experiments on frontier models, and improve pipelines for faster, safer software development.

Qualifications

• Bachelor's degree or equivalent required.
• Field of study relevant to the role as demonstrated through coursework or experience.
• Location-based hybrid policy requiring 25% office presence.

Responsibilities

• Design RL environments and coding tasks.
• Build reward signals and verifiers for code quality.

Skills

Software engineering

Python

Async programming

End-to-end ownership

Debugging across stack

Code quality

AI safety focus

Education

Bachelor's degree

Tools

PyTorch

Distributed training

CUDA

TPU

Job description

Anthropic Limited in New York is hiring a Research Engineer for the Code RL team. You will help our models write, edit, test, debug, and ship real software end-to-end, working on real codebases with real tools.

This role blends research and engineering: design RL environments, build reward signals, run experiments on frontier models, and improve pipelines for faster, safer software development.