Research Engineer, Benchmarks

About HUDHUD is building infrastructure to create RL training data and evals for frontier AI agents, as well as a marketplace to sell these to frontier labs through the HUD marketplace. Our platform is used by frontier labs, Fortune 500 companies, and startups. We’ve raised $16M from top VCs and were YC W25.About the roleWe’re looking for Research Engineers to build high-quality benchmarks for evaluating frontier agents on domain-specific tasks. You’ll build benchmarks that are technically rigorous, practically useful, and credible to frontier labs.ResponsibilitiesOwn the design, implementation, and quality of HUD’s internal agent benchmarksWork with subject-matter experts to define tasks and create domain-specific benchmarks that evaluate agents on realistic workflowsBuild infrastructure to reliably run models and agents against benchmark tasksDevelop metrics and analyses to understand benchmark difficulty, reliability, and failure modesValidate whether benchmark performance correlates with real-world evals, customer needs, and lab expectationsWrite clear documentation and benchmark reports that make results legible and credible to technical audiencesExperienceYou may be a good fit if you have:Proficiency in Python, Docker, and Linux environmentsPublished papers or written technical blogs on relevant topics such as public benchmarks and their limitations, model failure modes, etc. - please link in your applicationStrong understanding of what a “good benchmark” means and what makes one realistic, reliable, and usefulExperience working on environments and evalsCuriosity and ability to truly understand how workflows in various domains workStrong candidates may also:Be detail-oriented and able to spot subtle inconsistencies or edge cases in tasksBe able to reason from first principles about task design, scoring, and failure modesThrive in unstructured problem spacesEarly-stage startup experience with ability to work independently in fast-paced environmentsStrong communication skills for remote collaboration across time zonesWe prioritize technical aptitude and learning potential over years of experience. Motivated candidates are encouraged to apply even if they don't meet all criteria.Team & company detailsTeam Size: ~15 people currently, mostly full-time in-person, but some remote.Our team: Our team includes 4 International Olympiad medalists (IOI, ILO, IPhO), serial AI startup founders, and researchers with publications at ICLR, NeurIPS, etc.Company stage: We have 8 figures in funding and high revenue growth. We’re scaling profitably and quickly to meet very strong demand.LogisticsEmployment: Full-time.Location: On-site only, for now. You can join the team in the San Francisco Bay Area or Singapore offices.Visa Sponsorship: We provide support for relocation and visas for strong full-time candidates to the US or Singapore.Timeline: Applications are rolling. The process is 2 technical interviews and a 2-3 day work trial.What we offerCompetitive compensation100% covered top-of-the-line medical, dental, and vision from Blue Shield of CA (US employees)Lunch and dinner when you’re in the officeCompany-wide holiday break (Christmas Eve to New Year’s Day) on top of PTO and paid holidaysOther perks including an Equinox membership, 401k, and commuter benefits (US employees)Unlimited* access to tokens for ChatGPT, Claude Code, Cursor, etc. *By unlimited, we mean no one on our token usage leaderboard has ever hit a limit. So we have no idea what the limit is.Due to high volume, we may not actively respond to every application, but feel free to contact us at recruiting@hud.so or elsewhere if we missed your application!