Member of Technical Staff - AI Evaluation & Benchmark Research

About the Company

We're partnering with a stealth AI infrastructure startup building the data foundation for the next generation of frontier AI models. Rather than training models directly, the company develops the benchmarks, evaluation frameworks, and high-quality datasets that enable leading AI labs to build more capable, reliable, and production-ready systems. Working across domains such as computer use, finance, multimodal generation, and enterprise productivity, the team is redefining how AI models are evaluated and improved through world-class research and data infrastructure.

Company Snapshot

• $30M funded stealth AI infrastructure startup founded by leaders from a frontier AI lab and an AI infrastructure decacorn.
• Team includes researchers and engineers from Meta, Scale AI, Anthropic, and other leading AI organizations.
• Already partnering with top frontier AI labs across computer use, finance, multimodal AI, and enterprise productivity.
• One of the earliest dedicated research hires with significant influence over the company's research direction and evaluation strategy.
• Mission-driven team building the data infrastructure that enables frontier AI models to perform valuable real-world work.

Searching for Development & Programming roles that provide visa sponsorship? Connect with international employers through Development & Programming Jobs with Visa Sponsorship opportunities actively seeking talented professionals.

• Competitive compensation of $250K–$350K base plus equity, with visa sponsorship available.

Why You Should Join

• Lead research that directly influences how frontier AI models are evaluated and improved.
• Own benchmark design, evaluation methodology, and dataset strategy from the ground up.
• Publish impactful research while collaborating with some of the world's leading AI organizations.
• Join an exceptional team of researchers with deep experience across frontier AI labs and infrastructure companies.
• Shape the future of AI data quality and evaluation at one of the industry's most promising stealth startups.

Explore our comprehensive directory of visa sponsorship jobs from employers worldwide who are ready to sponsor talented international professionals.

About the Role

You'll join as a Member of Technical Staff leading research across LLM evaluations, benchmark design, and data quality. You'll design novel evaluation methodologies, build datasets that improve frontier models, conduct publishable research, and work closely with domain experts to define the next generation of AI evaluation infrastructure.

Qualifications

• 6–10 years of combined academic and industry AI/ML research experience.
• PhD in Machine Learning, Computer Science, Computer Vision, Statistics, or another quantitative discipline from a top-tier university (strongly preferred). Exceptional Master's candidates with outstanding publications will also be considered.
• Published research at premier conferences such as NeurIPS, ICML, ACL, or equivalent, ideally as a lead or first author.

Interested in opportunities specifically in United State? Discover our dedicated Visa Sponsorship Jobs in United State page featuring roles from top employers in this location.

• Deep expertise in LLM evaluation, benchmark design, dataset creation, and AI data quality.
• Strong engineering skills with Python and PyTorch, capable of designing experiments and collaborating on evaluation infrastructure.
• Previous experience at a frontier AI lab or AI infrastructure company is highly preferred.

Pay range and compensation package

• Compensation: $250K–$350K Base + Competitive Equity
• Location: New York City or San Francisco
• Work Model: Hybrid (4–5 days in office)
• Visa Sponsorship: Available, including visa transfer