Research Scientist - Frontier Benchmarks

ABOUT THE ROLE 

We're looking for a Research Scientist to lead the design of next-generation benchmarks and datasets that push the boundaries of frontier model evaluation. You'll define what "good" looks like across a range of hard tasks, drawing on conversations with customers and academic partners to ground your datasets in real performance gaps. You'll build both the benchmarks that measure those gaps and the training data that helps close them, then partner with delivery, product, and go-to-market to bring what you build into production.

This role is ideal for someone who wants to shape how the field measures progress in frontier AI, and who's energized by doing that work inside a fast-moving, cross-functional startup.

MAIN RESPONSIBILITIES 

• Design state of the art datasets that drive frontier model training and evaluation based on current model performance and academic partnerships 
• Translate benchmark insights into clear, compelling narratives that articulate the ROI of expert-curated data for customer-facing presentations, technical reports, and go-to-market materials.
• Work cross-functionally with data operations, product, engineering, and strategy to surface research findings that inform the company roadmap. 
• Stay at the frontier of LLM evaluation research and bring best practices into Snorkel's workflows
• Represent Snorkel's research externally through publications, blog posts, conference talks, and customer engagements that advance the conversation around data-centric AI

PREFERRED QUALIFICATIONS 

• Strong research background in AI/ML evaluation, NLP, or related fields, with a track record of rigorous experimental design — especially around measuring the impact of training and evaluation data on model behavior. 
• Exceptional communication skills — able to present complex technical findings clearly to both technical and non-technical audiences 
• Comfort operating in a fast-moving, cross-functional environment with ambiguous problem spaces 
• Genuine interest in GTM strategy, startup dynamics, and the commercial side of AI data services. 
• Ph.D. in machine learning, NLP, or a related field preferred; equivalent industry or research lab experience considered.