Member of the Technical Staff

We are looking for a Member of the Technical Staff with 5+ years of combined academic and industry research experience to lead the research behind evaluations and datasets that will enable the next wave of AI model improvement. You'll be one of the first dedicated research hires, shaping how the company thinks about data quality, LLM evaluation, and benchmark design across critical domains like life sciences and finance.

What will you be doing?

- Designing and owning benchmarks, evals, and dataset taxonomies that set the standard for data quality in AI

- Conducting independent research and publishing papers to establish the company as a thought leader in AI benchmarks

- Identifying where frontier models are failing and building datasets to address those gaps

- Partnering with domain experts and deployment leads to define what high-quality training and evaluation data looks like across verticals

- Driving the research agenda with autonomy — proposing new ideas, designing experiments, and dragging the team along with you

Key Requirements

- PhD in machine learning, computer science, computer vision, or a quantitative science (strongly preferred)

- Published research at top venues (e.g., ICML, NeurIPS) — ideally as a top author with cited work

- Deep familiarity with LLMs, benchmark design, eval methodology, and data quality for model improvement

- Based in New York or San Francisco and willing to work in-office 5 days/week (flexible to 4 days)

- Natural curiosity about model behavior with the ability to identify where AI is deficient and propose data-driven solutions