The perception and prediction team at Motional, authors of nuScenes (https://www.nuscenes.org), PointPillars (https://arxiv.org/abs/1812.05784), PointPainting (http://arxiv.org/abs/1911.10150), and CoverNet (https://arxiv.org/abs/1911.10298) is growing and we are adding engineers and researchers to join us in our mission to launch a level 5 autonomous taxi system. 

What You’ll Be Doing:

• Research and develop neural networks for perception problems such as object detection, instance segmentation, sensor fusion, traffic light detection etc.
• Develop clean C++ software for the perception modules that sit at the core of our autonomous vehicle perception and interface with all other key modules such localization, mapping, and planning.
• Own the full life cycle of new features development from proof of concept stage to on-car software integration by coordinating with the downstream teams.
• Develop core deep learning codebase for efficient training and testing pipelines.
• Conduct deep learning experiments, write reports, and file patents.
• Mentor junior researchers by providing guidance on research projects and design document reviews.

What We’re Looking For:

• Masters or PhD in Machine Learning, Computer Science, Applied Mathematics, Statistics, Physics or a related field.
• Experience designing, training, and analyzing neural networks for at least one of the following applications: Object detection, Image segmentation, Sensor fusion, Multitask learning, Traffic light detection, Active learning, and One shot learning. 
• 5+ years of experience in C++ software development and Fluency in Python.
• Experience with PyTorch or other deep learning frameworks.
• Experience in automotive or other real-time and embedded systems.

Bonus points: 

• Proven track record of publications in relevant conferences (CVPR, ICML, NeurIPS, ICCV, ICLR…)

_______________________________________________________________

(Colorado only*) Minimum salary of $172,020/year + bonus + equity + benefits
 *Note: Disclosure as required by sb19-085(8-5-20)

Company: