Research and develop efficient, end-to-end ML solutions for Perception with sensor fusion, including but not limited:
Obstacle detection and understanding (e.g. obstacles 3D location, motion properties, and fine-grained attributes)
Understanding of the drivable space and 3D occupancy
Map sensing (e.g. lane boundary and topology)
Scene understanding (e.g traffic light, short/long-term intent of vehicles, construction zone, etc.)
Develop efficient and robust onboard system
Develop efficient offboard loop to allow fast iteration on long-tail scenarios
Requirements:
Have strong abilities in both algorithms and C++ coding or have strong expertise in at least one of these fields: computer vision, machine learning, and model optimization
Solid skills in problem solving, algorithms, and data analysis
Good communication and coordination skills
Self-motivated and believe in the future of self-driving-cars
Plus:
Rich experience in C++ development, multithreading, memory management, computing optimization
Rich experience in multi-sensor fusion and 3d/2d tracking
