• [Road Geometry Direction] Track the latest advancements in road geometry perception in academia, including but not limited to lane lines, stop lines, crosswalks, road markers, and road topology.
• [Occupancy Direction] Follow the latest developments in occupancy network perception, researching camera, LiDAR, and radar-integrated occupancy perception solutions to achieve industry-leading technology. Implement these perception technologies in large-scale autonomous driving data lakes, providing cloud-based occupancy ground truth services for different sensor configurations and vehicle models.
• [Multimodal Direction] Keep up with the latest research in multimodal perception, developing end-to-end BEV (Bird's Eye View) perception solutions that integrate cameras, LiDAR, and radar to achieve industry-leading capabilities. Deploy these technologies in large-scale autonomous driving data lakes to provide cloud-based BEV ground truth services for various sensor configurations and vehicle models.
• [LiDAR Direction] Stay updated on the latest LiDAR perception research, focusing on dynamic and static obstacle detection using LiDAR to maintain a technological edge in the industry. Apply these perception techniques in large-scale autonomous driving data lakes to provide cloud-based 3D ground truth services for different vehicle sensor configurations.
  
  
  

• Master's degree or higher in Computer Vision, Pattern Recognition, Machine Learning, Electronic Information, Robotics, or related fields.
• Strong coding skills, proficient in at least one programming language such as Python or C++, and familiar with commonly used deep learning frameworks like PyTorch. ACM competition experience is a plus.
• Solid and relevant experience in 3D perception.
• Strong communication and teamwork skills, with the ability to quickly learn and master new domain knowledge.

All applications applied through our system will be delivered directly to the advertiser and privacy of personal data of the applicant will be ensured with security.