All Jobs
Benchmarking Engineer (Baselines & Evaluation — QuPracs)
You’ll design benchmark suites and evaluation harnesses.
You’ll keep results reproducible and easy to interpret.
The Role
Own benchmarking: reproducible baselines, fair comparisons, and clean reporting that prevents overclaims.
Responsibilities
- Create reusable benchmark datasets and harnesses.
- Define metrics and comparison methodology.
- Publish clear reports that state limits.
Requirements
- Experience building reliable evaluation pipelines.
- Strong programming fundamentals (Python preferred).
About QuPracs
We work in domains where hype is loud and uncertainty is real. Our job is to help teams make responsible decisions—and to prototype only when it teaches something measurable.