Research Engineer, Benchmarks
hud- Location
- Not specified
- Work mode
- On-site
- Type
- full time
- Listed
Applications go directly to hud. Ramai takes no fee for placement and no money for ranking.
[ About this role ]
Research Engineers at HUD will design, implement, and ensure the quality of internal agent benchmarks for evaluating frontier AI agents. Responsibilities include defining tasks with subject-matter experts, building infrastructure for model execution, developing metrics, and validating benchmark performance against real-world needs.
Skills and focus areas
- python
- docker
- linux
- benchmark design
- agent evaluation
- technical documentation
- data analysis
- workflow understanding
- model failure modes
Summary written by Ramai from the original posting. Full details and requirements are on hud’s careers page.
[ More at hud ]
Platform for building RL environments and evals
See all 37 open roles at hud →[ Similar roles at other startups ]
- Research Engineer, EvalsVariance
- Machine Learning ScientistRelace
- Tram Trainer - EmeaSphere
- Applied Ai Research EngineerBeam
- Ai Anime Researcher - LlmSpellbrush
- Rev Genomics (s17) Seeks Plant BiologistRev Genomics
[ Not quite right? ]
Tell the assistant what you’re after — stage, location, stack, visa sponsorship — and it searches every open role for you. A few questions are free, no account needed.