Code RL Research Engineer — Build Safe, Scalable AI

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

Job summary

Anthropic in San Francisco is looking for a Research Engineer to enhance AI systems by advancing their coding abilities—encompassing writing, editing, testing, and debugging real software.

You will design RL tasks and develop reward signals, run training experiments, and play a pivotal role in shaping the future of beneficial AI systems.

The compensation range for this position is USD $500,000 – $850,000 annually.

Qualifications

• Strong software-engineering skills with deep Python expertise, including async/concurrent programming.
• Experience owning systems end-to-end and debugging across the stack.
• Balance research exploration with engineering implementation.

Responsibilities

• Advance models' ability to write, edit, test, debug, and ship real software.
• Design RL environments and coding tasks, build the reward signals.
• Run training experiments on frontier models.

Skills

Software-engineering skills

Deep Python expertise

Debugging across the stack

Knowledge of code quality

Experience with reinforcement learning

Tools

PyTorch

CUDA

TPU

Job description

Anthropic in San Francisco is looking for a Research Engineer to enhance AI systems by advancing their coding abilities—encompassing writing, editing, testing, and debugging real software.

You will design RL tasks and develop reward signals, run training experiments, and play a pivotal role in shaping the future of beneficial AI systems.

The compensation range for this position is USD $500,000 – $850,000 annually.