About the Team The team at PICO is dedicated to leverage technologies such as computer vision, deep learning, SLAM, 3D reconstruction, and multi-sensor fusion, we continuously expand the ways humans interact with the virtual world through handheld controllers, bare-hand tracking, eye-tracking, and XR interactive accessories, enhancing the overall interaction experience.
Responsibilities：
- Lead the development of high-precision and low-latency hand tracking algorithms in XR scenarios, covering directions such as monocular/multiple vision and multi-sensor fusion
- Build a robust 3D gesture pose estimation model to solve the problems of extreme scenarios such as occlusion, fast motion and complex illumination
- Optimize the real-time inference performance of the algorithm on the mobile XR headset to achieve millimeter-level tracking accuracy
- Lead the construction of the MultiModal Machine Learning interaction algorithm framework (hand + eye movement + peripheral device) to create a natural XR interaction pattern
- Promote patent layout and publication of papers in accredited conferences (CVPR/ICCV/SIGGRAPH, etc.) to enhance the technical influence of the team
Requirements
Minimum Qualifications:
- Majored in Computer Vision, Pattern Recognition or Applied Mathematics, with more than 5 years of experience in algorithm R&D
- Familiar with the technical principles, advantages and disadvantages of commercial solutions such as ARKit Hand Tracking and Quest Hand Tracking
- Proficient in PyTorch framework and QNN deployment ecosystem, with practical experience in TensorRT end-side optimization
Preferred Qualifications:
- Experience in developing the core algorithm of HandTracking for XR products
- Published papers on gesture tracking in accredited conferences such as CVPR/ICCV/SIGGRAPH