Senior Software Engineer, Evaluation Flywheel — Autonomous Vehicles

Job Description

Own the strategy, architecture, and execution of the evaluation flywheel to ensure the trustworthiness of the autonomous driving stack. Build tooling for dataset curation and metric measurement while partnering with cross-functional teams to improve AI model development velocity.

Requirements: Requires a BS or MS in Computer Science or Robotics with over 12 years of software experience in autonomous vehicles or large-scale ML systems. Must have deep expertise in ML evaluation, metric design, and production-scale Python data pipelines.

Key Skills: Python, Data Engineering, ML Evaluation, Robotics, Autonomous Vehicles, Vision-Language Models, Dataset Curation, Metric Design, Closed-loop Simulation, Technical Leadership, Precision/Recall Methodology, Production-scale Pipelines, Agentic Techniques, Software Architecture, VLM-based Evaluation

Benefits: Equity, Benefits