Benchmark-Driven ML Evaluation & Security Engineer

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

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA is seeking an Evaluation/ML-Systems Engineer to own how we measure our program's progress. You will design metrics, baselines, and protocols, and build infrastructure that ties results to runs and code.

You will ensure evaluations are reproducible and trustworthy, partnering with security researchers and platform engineers. Your work will define what progress means for the program, with a focus on rigorous measurement, traceability, and evidence-driven conclusions across our AI safety

Qualifications

• Bachelor's degree (or equivalent experience) with 5+ years in ML engineering or evaluation.
• Evaluation experience: Designing benchmarks, metrics, and statistically sound comparisons for ML systems.
• Measurement rigor: A careful, skeptical approach to metrics, baselines, and claims.
• Engineering skills: Solid Python engineering for shared infrastructure, including experiment tracking and data pipelines.

Responsibilities

• Build evaluation infrastructure and reproducibility systems for benchmarks.
• Define metrics and protocols and ensure traceability to code and runs.
• Design experiments with trusted, auditable results; enable reproducibility across teams.
• Collaborate with security researchers and platform engineers to create trustworthy evaluations.

Skills

ML engineering

Evaluation

Measurement rigor

Python

Experiment tracking

Data pipelines

Education

Bachelor's degree or equivalent experience

Tools

Python

Job description

NVIDIA is seeking an Evaluation/ML-Systems Engineer to own how we measure our program's progress. You will design metrics, baselines, and protocols, and build infrastructure that ties results to runs and code.

You will ensure evaluations are reproducible and trustworthy, partnering with security researchers and platform engineers. Your work will define what progress means for the program, with a focus on rigorous measurement, traceability, and evidence-driven conclusions across our AI safety