Responsibilities: Assist in building and refining perception algorithms for 3D object detection, tracking, segmentation, and scene understanding
Analyze sensor data (e.g., images, video, lidar, radar) to improve model accuracy and robustness
Support data preprocessing, labeling, augmentation, and validation workflows
Conduct experiments to benchmark perception models and propose improvements
Collaborate with cross-functional teams (Behaviors, Actions, Platforms teams) to integrate perception outputs into downstream decision-making systems
Document findings, tools, and results in clear and reproducible formats
Required Skills: A Masters/PhD degrees in Computer Science, Machine Learning, Robotics or a related field
Proficient at Python and/or C++
Coursework or project experience in computer vision, machine learning, and data processing
Familiarity with popular deep learning frameworks such as PyTorch or TensorFlow
Experience with image/video processing tools...