ML Evaluation & Security Systems Engineer

NVIDIA Corporation; Santa Clara, Northern (CA, KY); Hybrid; USD 152,000 - 242,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA Corporation in Santa Clara is seeking an Evaluation/ML-Systems Engineer to own how we measure the program, building benchmarking and reproducibility systems, and defining metrics and protocols that make results meaningful and traceable.

You will design the protocols, map results to code and runs, and automate measurements so findings are reviewable. Collaboration with security researchers and platform engineers is essential.

Qualifications

• Bachelor's degree with 5+ years in ML engineering or evaluation.
• Experience designing benchmarks, metrics, and statistically sound comparisons for ML systems.
• A careful, skeptical approach to metrics, baselines, and claims.
• Solid Python engineering for shared infrastructure, including experiment tracking and data pipelines.

Responsibilities

• Design and build evaluation infrastructure for benchmarking and reproducibility.
• Define the metrics and protocols we measure against.
• Map every result to the code and runs that produced it.
• Keep findings reviewable and conclusions traceable.
• Collaborate with security researchers and platform engineers to design trustworthy experiments.
• Automate measurement workflows so teams can focus on research questions.

Skills

ML engineering

Evaluation design

Benchmarking

Metrics

Experiment tracking

Education

Bachelor's degree or equivalent experience

Tools

Python

Data pipelines

Experiment tracking

Reproducible workflows

Job description

NVIDIA Corporation in Santa Clara is seeking an Evaluation/ML-Systems Engineer to own how we measure the program, building benchmarking and reproducibility systems, and defining metrics and protocols that make results meaningful and traceable.

You will design the protocols, map results to code and runs, and automate measurements so findings are reviewable. Collaboration with security researchers and platform engineers is essential.