Senior Evaluation Engineer — Autonomous Driving Flywheel

NVIDIA; Washington (Washington County); 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 evaluating progress through a rigorous eval flywheel. We seek a senior engineer to own this engine end‑to‑end, from architecture and data pipelines to metrics and trust with partner teams.

You will lead the design of golden datasets, metric design (precision/recall), and production‑level tooling. Collaborate with model developers and cross‑team leaders to accelerate evaluation while maintaining high standards and reliability.

Qualifications

• 12+ years building software, with autonomous vehicles, robotics, or large‑scale ML systems.
• Strong Python and data engineering skills for production‑scale pipelines.
• Experience evaluating ML or robotic systems: metric design, ground‑truth datasets, precision/recall.

Responsibilities

• Own the eval flywheel's strategy and architecture from data to metrics to trusted results.
• Build tooling for dataset pipelines, metric performance, and quality reporting.
• Collaborate with senior engineers and AI model teams to speed evaluation iterations.
• Set high standards for evaluation quality, health of datasets, and release processes.
• Communicate clearly with engineers and leaders across teams at pace.

Skills

Python

Data engineering

Production-scale pipelines

Technical leadership

Communication

ML evaluation

Education

BS/MS in Computer Science/Robotics or related field

Tools

Golden datasets

Versioning

ML evaluation tooling

Job description

NVIDIA is building the future of autonomous driving and evaluating progress through a rigorous eval flywheel. We seek a senior engineer to own this engine end‑to‑end, from architecture and data pipelines to metrics and trust with partner teams.

You will lead the design of golden datasets, metric design (precision/recall), and production‑level tooling. Collaborate with model developers and cross‑team leaders to accelerate evaluation while maintaining high standards and reliability.