Research Fellow

About the Role

As a Research Fellow at Snorkel, you’ll build open benchmarks and evaluation environments that help shape how AI progress is measured. This fellowship is for PhD students and postdocs who want to turn important questions in their fields into new ways to evaluate AI capabilities.

You’ll own the project from the initial research question through public release, setting its direction and leading its development. A Snorkel researcher will serve as your co-advisor, and you’ll have access to Snorkel’s broader resources, including paid time from credentialed domain experts and compute to run experiments and evaluate frontier models.

You’ll retain your academic affiliation while spending at least one day a week with Snorkel’s research team, including in person in our San Francisco or New York offices where applicable.

What you’ll do

• Scope and lead a new benchmark, dataset, or environment in a domain where current evaluations fall short
• Define the task specification, rubrics, and reference answers with domain experts from Snorkel's network, and run the expert review process
• Release the research artifact publicly, with you as lead author. 
• Join weekly research meetings to share progress, receive feedback, and contribute to other researchers’ projects

What you'll get

• A Snorkel research co-advisor matched to your project
• Domain Experts, compute, and engineering support for your project
• An open-source academic artifact released as a part of your work
• Time with Snorkel’s research team and other fellows, plus access to research and community events
• Research communications support to share your findings with the broader community
• A firsthand view of how a leading data research lab bridges academic research and work with frontier labs and enterprises

What we’re looking for: 

• You’re excited to advance how AI is evaluated in your field and have the research background to design and build open benchmarks, datasets, or environments.
• You have demonstrated the ability to turn research ideas into working code, datasets, tools, or other usable research artifacts
• You work well with domain experts outside your own field and can turn their judgment into a specification
• You can 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

Salary range(s) for this role

Hourly ranges from $85-$165+/hour. Actual compensation will be determined based on factors including skills, qualifications, experience, and geographic location.

#LI-DNI