← All roles

Research Engineer, Benchmarks

HUD· Engineering & Research
Apply on company site
San Francisco, Singapore, Remote (Asia), Remote (North America)$100k - $230kFull-timePosted 3mo ago

About the role

Roles focus on designing and implementing high-quality benchmarks to evaluate frontier agents on domain-specific tasks, ensuring benchmarks are rigorous, practical, and credible to labs and customers.

Responsibilities

  • Own the design, implementation, and quality of HUD’s internal agent benchmarks
  • Work with subject-matter experts to define tasks and create domain-specific benchmarks that evaluate agents on realistic workflows
  • Build infrastructure to reliably run models and agents against benchmark tasks
  • Develop metrics and analyses to understand benchmark difficulty, reliability, and failure modes
  • Validate whether benchmark performance correlates with real-world evals, customer needs, and lab expectations
  • Write clear documentation and benchmark reports that make results legible and credible to technical audiences

Qualifications

  • Proficiency in Python, Docker, and Linux environments
  • Published papers or written technical blogs on relevant topics such as public benchmarks and their limitations, model failure modes, etc. – please link in your application
  • Strong understanding of what a 'good benchmark' means and what makes one realistic, reliable, and useful
  • Experience working on environments and evals
  • Curiosity and ability to truly understand how workflows in various domains work
  • Strong candidates may also: detail-oriented, able to spot inconsistencies or edge cases, reason from first principles about task design, scoring, and failure modes, thrive in unstructured problem spaces, early-stage startup experience, strong remote communication skills

Skills

Required:PythonDockerLinux environmentsBenchmark designEvidence writing & documentation

Benefits

  • Competitive compensation
  • 100% covered top-of-the-line medical, dental, and vision (US and Singapore employees)
  • Lunch and dinner for in-office employees
  • Company-wide holiday break (Christmas Eve to New Year’s Day) on top of PTO and paid holidays
  • 401k with a 4% match
  • Equinox membership and commuter benefits (US employees) and health/wellness stipend (Singapore employees)
  • Unlimited access to tokens for ChatGPT, Claude Code, Cursor, etc. (no known usage limits)
  • Two top-floor offices in San Francisco’s Union Square and Singapore’s Raffles Place
  • Annual travel budget to visit either office
Last updated Oct 25, 2026. Interested? Apply on the company site.

About HUD

The platform for building RL environments

The platform for building RL environments. Train specialized agents, evaluate models, and deliver frontier‑grade post‑training data to labs.

AI benchmarkingEnvironment SDKGRPO trainingHUD Vendor PlatformMCP environmentsRL environmentsTraining + Eval Platformagent training
Company profileWebsite

More open roles at HUD