Software Engineer (Perception, Fallback Stack)

• As a Perception Software Engineer on the Autonomy team, you will build the perception system for L4 autonomous trucks operating at highway speeds
• The stack combines state-of-the-art machine learning - multi-modal 3D detection, BEV representations, learned tracking - with rigorous classical perception: state estimation, multi-object tracking, and sensor fusion
• You will own problems end-to-end, from model architecture and training through onboard deployment and on-road validation
• This is safety-critical software: every capability passes formal simulation, closed-course, and safety sign-off gates before it reaches public roads
• You will collaborate daily with behavior/planning engineers, systems and safety engineers, and validation teams
• Design, train, and deploy deep learning models for 3D object detection across LiDAR, camera, and radar sensors
• Build multi-sensor fusion architectures that combine independent detection and classification streams
• Characterize perception failure modes, build targeted evaluation sets, and hill-climb system-level metrics
• Build and operate the data engine: shadow-mode comparison against production, automated data mining, and retraining loops
• Contribute to camera- and LiDAR-based localization perception under degraded conditions
• Take your work through the full safety validation pipeline before it operates on public roads

Preferred experience

• Bachelor’s degree in Computer Science, Robotics, Electrical Engineering, or a related field
• Hands-on experience training and deploying deep learning models in production (e.g., PyTorch)
• Solid grounding in classical perception: multi-object tracking, state estimation, and 3D geometry
• Strong proficiency in Python and C++
• 4+ years of professional experience in ML-based perception, computer vision, or robotics
• If you’re excited about this role but your past experience doesn’t align perfectly with every qualification in the job description, we encourage you to apply anyway
• Background in safety-critical or automotive software development
• Experience with multi-sensor calibration and fusion
• Experience optimizing models for onboard/embedded GPU inference
• Experience in a startup or fast-paced environment
• Experience working in modern ML-based perception for autonomous systems