ML Evaluation & Benchmarking Systems Engineer

NVIDIA; North Carolina; On-site; USD 152,000 - 242,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA in the United States, North Carolina is seeking an Evaluation/ML-Systems Engineer to own how we measure the program and separate real capability from anecdote. You will design benchmarks, architect reproducible metrics, and map results to code and runs, ensuring traceability across the pipeline.

You will partner with security researchers and platform engineers to create trusted experiments, automate measurement, and enable transparent, credible evaluation as the program scales.

Qualifications

• Bachelor's degree or equivalent with 5+ years in ML engineering or evaluation.
• Experience designing benchmarks, metrics, and statistically sound comparisons.
• Rigorous measurement mindset with careful baselines and claims.
• Strong Python engineering for shared infrastructure, experiment tracking, and data pipelines.

Responsibilities

• Build and maintain evaluation infrastructure for benchmarking and reproducibility.
• Define metrics and protocols to measure ML systems.
• Ensure traceability by mapping results to code and runs.
• Keep findings reviewable and conclusions traceable.

Skills

Python

ML engineering

Evaluation design

Data pipelines

Education

Bachelor's degree

Job description

NVIDIA in the United States, North Carolina is seeking an Evaluation/ML-Systems Engineer to own how we measure the program and separate real capability from anecdote. You will design benchmarks, architect reproducible metrics, and map results to code and runs, ensuring traceability across the pipeline.

You will partner with security researchers and platform engineers to create trusted experiments, automate measurement, and enable transparent, credible evaluation as the program scales.