Senior Machine Learning Perception Engineer, Fallback Driving System

What you'll do

• Design, train, and evaluate ML perception models for object detection, segmentation, tracking, and prediction.
• Develop and maintain the secondary stack perception model to enable safe fallback autonomy.
• Define ML success metrics and drive systematic experimentation to improve model performance and robustness.
• Analyze large-scale datasets and build data selection and labeling strategies for long-tail scenarios.
• Implement efficient training and inference pipelines using model optimization techniques like pruning and quantization.
• Integrate models into production systems by collaborating with software and infrastructure engineers.
• Translate system requirements into concrete ML model requirements, metrics, and validation criteria.
• Contribute to verification and validation strategies including offline evaluation, simulation, and on-road testing.

What we're looking for

• BS, MS, or PhD in Machine Learning, Robotics, Computer Science, or a related technical field; or equivalent practical experience.
• 3–5 years of experience developing ML solutions in perception, prediction, and/or autonomous driving or related domains.
• Strong experience with multi-modal sensor data including camera, lidar, and radar for preprocessing, synchronization, and fusion.
• Deep expertise in modern deep learning for 2D/3D object detection, semantic/instance segmentation, and multi-object tracking.
• Proficiency in Python and at least one major ML framework such as PyTorch, TensorFlow, or JAX.
• Solid software engineering skills including experience working in C++ or similar languages in large, collaborative codebases.
• Experience deploying ML models on embedded or resource-constrained platforms, including model optimization and performance tuning (preferred).
• Experience with AV/ADAS perception stacks, robotics, or ROS (preferred).