Research Fellow

The role

You will build open benchmarks and evaluation environments to measure AI progress. You will own projects from the initial research question through public release.

What you will do

• Scope and lead a new benchmark, dataset, or environment
• Define task specification, rubrics, and reference answers with domain experts
• Run the expert review process
• Release the research artifact publicly as lead author
• Join weekly research meetings to share progress and receive feedback
• Contribute to other researchers' projects

Required qualifications

• PhD student or postdoc
• Research background to design and build open benchmarks, datasets, or environments
• Ability to turn research ideas into working code, datasets, tools, or other usable research artifacts
• Ability to work well with domain experts outside your own field
• Ability to scope a project to a public release within the fellowship term

Nice to have

• Publications at venues such as NeurIPS, ICML, ICLR, or the top venues in your own discipline
• Experience with agentic evaluation, RL environments, or LLM evaluation harnesses
• Deep expertise in a domain where expert-level evaluation is scarce, such as the sciences, medicine, law, finance, or engineering

Benefits

• A Snorkel research co-advisor
• Domain Experts, compute, and engineering support
• An open-source academic artifact
• Time with Snorkel research team and other fellows
• Access to research and community events
• Research communications support

About the company

Snorkel AI is a frontier AI data lab founded out of the Stanford AI Lab in 2019. The company works with leading AI labs and enterprises to create datasets, benchmarks, evals, and custom solutions.