Where you can live
Open to people living in United States.
Listed location: New York City, NY (Hybrid); San Francisco, CA (Hybrid); United States (Remote)
Read from the posting text by our automatic check, which can be wrong. Confirm in the posting before you apply.
What the job is
Designs, implements and runs reinforcement learning training methods for large language models, and uses evaluation results to improve tasks, environments and training data.
What they ask for
- Research and implement reinforcement learning algorithms and training recipes for large language models
- Build data pipelines that generate high-quality training signals for RL workflows
- Prototype and iterate on end-to-end RL training recipes using training and evaluation results
- Work with research, ML engineering, data and delivery teams to diagnose training results and validate improvements
- Stay current with large-scale distributed LLM training and scalable RL methods
Nice to have
- Deep expertise in RL for language models, including multi-turn and long-horizon tasks
- Experience training or fine-tuning 30B+ parameter language models at scale
- Experience with large-scale RL training pipelines and cloud or cluster infrastructure
This is a summary written by software from the company's posting. The posting is the source.
More remote jobs at Snorkel AI