Ir para o conteúdo
AI.info

jobs

Research Scientist - RL Training

About Snorkel Snorkel AI is the frontier AI data lab, helping teams build the data and environments behind high-performing frontier and agentic AI. We combine technology with research-driven AI data…

Em inglês

Company
Snorkel AI
Location
New York City, NY (Hybrid); San Francisco, CA (Hybrid); United States (Remote)
Status
Open
Posted
2026-05-29 21:22 UTC

Snorkel AI is hiring a Research Scientist for reinforcement learning work aimed at LLM training and alignment. The person will implement methods such as GRPO, RLHF, RLAIF, DPO, and reward modeling; build pipelines that produce preference datasets and reward signals; and prototype end-to-end RL training recipes for customer data products. The posting asks for deep RLHF or reward-modeling expertise, experience training 30B+ models with distributed infrastructure, Python, PyTorch, HuggingFace, and RL frameworks such as Verl and SkyRL. A PhD is preferred.

Original job posting