Nuro is looking to define the Perception architecture for the Nuro Driver, specifically focusing on the Perception Foundation Encoder, which is responsible for compressing raw sensor data into a unified feature representation. This role aims to develop training techniques for this foundational encoder to improve functionalities like object detection, tracking, mapping, and scene understanding, while balancing performance, latency, and complexity.
Requirements
- Ph.D. level research experience in some of the following areas: multi-model models, large multi-task vision models, large scale model training, and model distillation.
- 3+ years working deeply on an ML project with material contributions.
- Strong SWE fundamentals and has demonstrated SWE experience in both high and low-level languages (Python and C++)
- Publications at some of the major conferences (e.g., CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, CoRL, RSS, ICRA).
Responsibilities
- help define the Perception architecture of Nuro Driver for years to come
- develops the training techniques for obtaining such a foundational encoder
- apply your deep understanding and experience in state-of-the-art machine learning to achieve a fine balance between model performance, onboard latency, and maintenance complexity
- define the Perception architecture
- compressing raw sensor data (cameras, lidar, radar, and audio) into a unified feature representation
- develops the training techniques for obtaining such a foundational encoder
Other
- Experience communicating clearly on complex technical topics across a range of stakeholders and leadership.
- At Nuro, we celebrate differences and are committed to a diverse workplace that fosters inclusion and psychological safety for all employees.
- Nuro is proud to be an equal opportunity employer and expressly prohibits any form of workplace discrimination based on race, color, religion, gender, sexual orientation, gender identity or expression, national origin, age, genetic information, disability, veteran status, or any other legally protected characteristics.
- This position is also eligible for an annual performance bonus, equity, and a competitive benefits package.
