Senior Software Engineer, Evaluation Flywheel — Autonomous Vehicles

Own the evaluation “flywheel” that turns road and simulation driving data into curated golden datasets and precision/recall metrics used to decide what ships in NVIDIA’s self-driving stack. Set standards for evaluation quality through dataset curation, health/versioning, and reliable release processes. Build production-scale tooling for self-serve pipelines and reporting, and partner across test engineering, behavior planning, infrastructure, and AI model developers to speed evaluation iteration.