Research Engineer – Benchmarks

hud (YC W25)

. Build high-quality benchmarks for evaluating frontier agents on domain-specific tasks .

Posted 9/23/2026full-timeSan Francisco • California • United StatesMid-LevelSeniorWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates proficiency in Python, Docker, and Linux environments to build and evaluate domain-specific benchmarks. Capable of designing reliable metrics and analyses while effectively communicating findings to technical audiences.

Highest-signal resume keywords

Proficiency In PythonExperience With DockerStrong Understanding Of Benchmark DesignDetail-Oriented AnalysisStrong Communication Skills

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

PythonBenchmark DesignMetric DevelopmentTask EvaluationAnalytical Skills

Soft Skills

CuriosityDetail-OrientedAbility To Thrive In Unstructured EnvironmentsStrong Communication Skills

Tools & Technologies

DockerLinux

Industry Keywords

BenchmarkingModel EvaluationReal-World CorrelationTechnical DocumentationStartup Experience

Tech Stack

Tools & technologies

DockerLinuxPython

About the role

Key responsibilities & impact

Build high-quality benchmarks for evaluating frontier agents on domain-specific tasks
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 evaluating 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 evaluations, customer needs, and lab expectations
Write clear documentation and benchmark reports for technical audiences
Participate in a 2–3 day work trial during the hiring process

Requirements

What you’ll need

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.; link in application
Strong understanding of what makes a benchmark realistic, reliable, and useful
Experience working on environments and evals
Curiosity and ability to understand workflows in various domains
Detail-oriented and able to spot subtle inconsistencies or edge cases in tasks
Ability to reason from first principles about task design, scoring, and failure modes
Ability to thrive in unstructured problem spaces
Early-stage startup experience and ability to work independently in fast-paced environments
Strong communication skills for remote collaboration across time zones
Ability to work hours that 70–80% overlap with either San Francisco or Singapore time zones for remote work
Technical aptitude and learning potential; years of experience are not required

Benefits

Comp & perks

100% covered top-of-the-line medical, dental, and vision from Blue Shield of CA (US employees)
Lunch and dinner when you’re in the office (in-office employees)
Company-wide holiday break (Christmas Eve to New Year’s Day) on top of PTO and paid holidays
PTO and paid holidays
Equinox membership (US employees)
401k (US employees)
Commuter benefits (US employees)
Unlimited* access to tokens for ChatGPT, Claude Code, Cursor, etc.
Support for relocation and visas for strong full-time candidates to the US or Singapore
Competitive compensation