Research Scientist - RL Training

The role

This Research Scientist will work on reinforcement learning for training and aligning large language models. You will translate research ideas into preference datasets, reward models, and RL-ready corpora.

What you will do

• Research and implement reinforcement learning techniques including GRPO, RLHF, RLAIF, DPO, and reward modeling.
• Translate techniques into data products like preference datasets and reward signals.
• Design and build data pipelines that generate high-quality training signal for RL workflows.
• Prototype and iterate on end-to-end RL training recipes.
• Work with research scientists, ML engineers, and delivery teams to translate research into customer-ready products.
• Stay current with developments in large-scale multi-node LLM training, alignment research, and scalable RL methods.
• Contribute to Snorkel's research publications and internal knowledge base.

Required qualifications

• Python proficiency
• ML frameworks proficiency, especially PyTorch and HuggingFace
• Hands-on experience with RL frameworks such as Verl and SkyRL
• Solid software engineering fundamentals

Nice to have

• Deep expertise in reinforcement learning from human or AI feedback, reward modeling and credit attribution
• Experience training or fine-tuning 30B+ large language models at scale
• Familiarity with distributed training infrastructure
• Familiarity with ML infrastructure and cloud platforms and tools (AWS, GCP, Kubernetes, Slurm, etc.)
• Experience with large-scale RL training pipelines
• Ph.D. in machine learning, reinforcement learning, or a related field

About the company

Snorkel AI is the frontier AI data lab, helping teams build the data and environments behind high-performing frontier and agentic AI. Founded out of the Stanford AI Lab in 2019, Snorkel works with leading AI labs and enterprises.