Role

Develop frontier AI benchmarks and datasets, working with research partners, customers, and internal data, product, and engineering teams.

Responsibilities

• Design datasets for frontier model training and evaluation.

• Analyze benchmark results and communicate research findings.

• Apply current LLM evaluation research to workflows.

• Collaborate across research, data operations, product, engineering, and strategy.

• Represent research through publications, talks, reports, and customer engagements.

Requirements

• Strong research background in AI/ML evaluation, NLP, or related fields.

• Experience with rigorous experimental design and evaluating training/evaluation data.

• Excellent technical and non-technical communication skills.

• Comfortable with fast-paced, cross-functional environments.

• Interest in AI data services and startup/GTM strategy.

• PhD in ML, NLP, or related field preferred; equivalent industry/research experience considered.