Senior AI Evaluation Architect – Autonomous Driving

NVIDIA; North Carolina; On-site; USD 224,000 - 357,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA is building the future of autonomous driving and seeks a senior engineer to own the eval flywheel—turning road and simulation data into trusted, production-grade evaluation results. This hands-on leadership role shapes architecture, quality, and adoption across teams, from data pipelines to metric reporting.

We value independent execution, proactive communication, and 12+ years in software for autonomous systems or ML.

Qualifications

• 12+ years of software development experience, including autonomous vehicles, robotics, or large ML systems.
• Strong Python and data engineering skills for production-scale pipelines.
• Deep experience evaluating ML/robotic systems: metrics, datasets, and pipelines.
• BS or MS in Computer Science, Robotics, or a related field (or equivalent).

Responsibilities

• Own the eval flywheel architecture, quality, and adoption end-to-end.
• Define evaluation standards for golden datasets, versioning, and health.
• Build tooling for dataset pipelines and metric performance reporting.
• Collaborate with test engineering, behavior planning, and infrastructure teams.
• Work with AI model developers to speed evaluation iterations, including VLM-based approaches.

Skills

Python

Data engineering

ML systems

Technical leadership

Education

BS/MS in CS/Robotics

Job description

NVIDIA is building the future of autonomous driving and seeks a senior engineer to own the eval flywheel—turning road and simulation data into trusted, production-grade evaluation results. This hands-on leadership role shapes architecture, quality, and adoption across teams, from data pipelines to metric reporting.

We value independent execution, proactive communication, and 12+ years in software for autonomous systems or ML.