Research Engineer RL Engineering
2 months agoSeniorSalary: 500K - 850KSan Francisco, CA | New York City, NY | Seattle, WAHybridAiJobs by Anthropic
AnthropicVisit Anthropic website
AI safety and research company building reliable, interpretable, and steerable AI systems, including the Claude product family and developer platform.
Series F+Recently funded61 current maintainers56 active leads24 new active leads28 lead step-downs8 early lead departures
San Francisco, United States
Funding history
About Anthropic
Anthropic PBC develops frontier AI systems and deploys them through Claude products and the Claude Platform, with a stated focus on safety, interpretability, and steerability.
Skills
Candidate Availability
About the Role
You will build, maintain, and improve the algorithms and systems used to train models with reinforcement learning. You will improve their speed, reliability, and usability, profile training pipelines, automate test training jobs, support new model architectures, and diagnose performance problems.
Requirements
- Software engineering
- System
- Tooling
- Large-scale distributed system
- Large-scale large language model training
- Python
- Large language model fine-tuning algorithm
- RLHF
Responsibilities
- Build, maintain, and improve model-training algorithms and systems
- Improve the speed, reliability, and usability of training systems
- Profile reinforcement-learning pipelines
- Build systems that launch test training jobs
- Adapt fine-tuning systems to new model architectures
- Build instrumentation to detect and eliminate Python GIL contention
- Diagnose and fix training-performance issues
- Implement stable and fast training algorithms
Benefits
- Visa sponsorship
- Equity donation matching
- Vacation leave
- Parental leave
- Flexible working hours
