Anthropic
San Francisco or New York City

Research Engineer, Code RL (Reinforcement Learning)

HybridPosted 6 days agoVisa Sponsorship

We tailor your resume to this role and apply for you in seconds.

Apply to Research Engineer, Code RL (Reinforcement Learning) at Anthropic

Job details

Location
San Francisco or New York City
Work type
Hybrid
Visa
Sponsorship available
Posted
6 days ago
Apply on
job-boards.greenhouse.io

About this role

Bachelor's degree or equivalent; strong software-engineering skills with deep Python expertise (async/concurrent); experience designing RL environments, building verifiers/eval harnesses, PyTorch and distributed training, CUDA/TPU/GPU performance optimization preferred.

What you'll do at Anthropic:

  • designing environments
  • running experiments
  • building verifiers

Apply to this Research Engineer, Code RL (Reinforcement Learning) role at Anthropic with a tailored resume on ApplyBolt.

Ready to apply to Anthropic?
We tailor your resume to this role and apply for you.

About Anthropic

Anthropic
San Francisco or New York City