◆ AfterJournal
AI apps, startups and the people building them
Author guidelines
·
Write for us
·
Contact
Jobs
/ Research / Research Engineer, Code RL (Reinforcement Learning)
Research Engineer, Code RL (Reinforcement Learning)
Anthropic · San Francisco, CA; New York City, NY
◉ Hybrid
◆ Research ▣ Full-time ⏫ Senior $ USD 500k-850k/year
Apply now →
0 applied · 0 views
The Code RL team at Anthropic uses reinforcement learning to improve how models write, test and debug software. The job mixes research with engineering.
- Design reinforcement learning environments and coding tasks
- Build reward signals and verifiers that define good code
- Run training experiments on large models and analyze results
- Improve the speed of training pipelines
Requirements
- Strong software engineering background
- Experience with machine learning research or reinforcement learning
- Ability to debug complex training systems
This is a hybrid full time position at senior level, based in San Francisco, CA; New York City, NY.
Day to day work includes reading papers, running experiments and sharing results with colleagues.
Candidates should check the full posting for exact qualifications, pay and benefits.
Apply on the company's careers page.
Similar jobs
◆ Newsletter
Ideas worth your inbox.
The best new stories, startups and AI tools every week. No noise, unsubscribe anytime.