Role

Lead a research team focused on AI evaluation, error analysis, and data valuation to improve model performance and guide Snorkel’s data strategy.

Responsibilities

• Lead a multi-quarter roadmap for evaluation, error analysis, and data valuation.

• Analyze model failures and benchmarks to identify capability gaps and data priorities.

• Develop methods to measure how Snorkel data improves model performance.

• Hire, lead, and develop researchers while maintaining high standards for quality and execution.

• Connect research findings with Product, GTM, and customers.

Requirements

• 7+ years in applied AI, ML, or research; 4+ years managing technical teams.

• Strong ability to turn research into business and customer outcomes.

• Strong AI/ML market and competitive judgment.

• Expertise in LLM evaluation, benchmarking, and model behavior analysis.

• Strong analytical, communication, and storytelling skills.

• Data valuation/attribution experience is a plus.

• Experience with frontier labs, public benchmarks, or commercial AI data/evaluation products is a bonus.