Snorkel AI is seeking a Research Scientist to advance reinforcement learning for training and aligning large language models. The role focuses on generating data, reward signals, and training procedures that guide LLM behavior, supporting Snorkel's data-as-a-service offerings.
You will work with research, engineering, and delivery teams to turn RL ideas into practical data products, publish findings, and push the boundaries of scalable RL in frontier AI environments.
#J-18808-Ljbffr
For the RL Scientist for LLM Alignment & Data-Driven Training position at Snorkel, we are reviewing applications now.
Take a moment to read everything above and see whether this role is right for you.
This posting is for the RL Scientist for LLM Alignment & Data-Driven Training role at Snorkel, based in San Francisco, CA, United States.
We are looking to fill the RL Scientist for LLM Alignment & Data-Driven Training position at Snorkel in San Francisco, CA, United States.