Lead Researcher — Frontier AI Benchmarks & Evaluation

Snorkel AI; United States; Remote; USD 231,000 - 390,000; Full time

Job summary

Snorkel AI is expanding its Open Benchmarks Grants program to advance frontier evaluation research. We seek researchers who can shape evaluation methodologies, review proposals, and lead collaborative efforts with senior researchers to strengthen ideas and allocate grants.

You will work with grantees, Research Fellows, and Snorkel research leads to define benchmarks, design experiments, and turn findings into actionable artifacts for the community.

Qualifications

• A research track record in evaluation.
• Experience with benchmarks and evaluation methods.
• Demonstrated ability to design rigorous experiments.
• Hands-on technical depth and implementation skill.
• Strong technical communication and collaboration leadership.
• Ability to drive cross-functional research collaboration.

Responsibilities

• Shape our research bets in open benchmarks & evaluation.
• Identify gaps in how frontier AI is evaluated.
• Review proposals with Snorkel’s senior researchers and collaborators to strengthen ideas and allocate Open Benchmark Grants.
• Advance frontier evaluation research with our research partners.
• Define measures, design tasks and experiments, and turn learnings into reusable artifacts.
• Drive adoption and scientific exchange with frontier labs.
• Collaborate with lab researchers to measure needs and interpret benchmark results.

Job description

Snorkel AI is expanding its Open Benchmarks Grants program to advance frontier evaluation research. We seek researchers who can shape evaluation methodologies, review proposals, and lead collaborative efforts with senior researchers to strengthen ideas and allocate grants.

You will work with grantees, Research Fellows, and Snorkel research leads to define benchmarks, design experiments, and turn findings into actionable artifacts for the community.