Senior Machine Learning Perception Engineer - Fallback Driving System

At General Motors, our product teams are redefining mobility. Through a human-centered design process, we create vehicles and experiences that are designed not just to be seen, but to be felt. We’re turning today’s impossible into tomorrow’s standard —from breakthrough hardware and battery systems to intuitive design, intelligent software, and next-generation safety and entertainment features.   Every day, our products move millions of people as we aim to make driving safer, smarter, and more connected, shaping the future of transportation on a global scale. As a Senior Machine Learning Engineer   on   the State Estimation and Mapping (SEAM) organization, you will develop and improve the ML   perception   model that powers the secondary (fallback) autonomy stack for Super Cruise 3. You will focus on building robust   perception   from multi‑modal   camera , lidar, and radar data so the vehicle can safely bring itself to a stop when the primary autonomy stack is unavailable.   You will lead the design, implementation, and continuous improvement of ML models for object detection, segmentation, tracking, and prediction, working closely with partner teams across   perception , planning, controls, and safety.

Design, train, and evaluate ML   perception   models for object detection, semantic/instance segmentation, tracking, and short‑horizon prediction using multi‑modal camera, lidar, and radar data.   Develop and   maintain   the secondary stack   perception   model that enables the fallback autonomy system to safely bring the vehicle to a minimal risk condition when the primary system experiences a fault.   Define clear ML success metrics (e.g., precision/recall, latency, robustness under edge cases) and drive systematic experimentation to improve model performance against those metrics.   Analyze large‑scale datasets, curate challenging scenarios, and build data   selection   and labeling strategies that improve robustness for long‑tail and degraded‑sensor conditions.   Implement efficient training and inference pipelines, including model optimization techniques (e.g., pruning, quantization, distillation) to meet on‑vehicle compute and latency budgets.   Collaborate with software and infra engineers to integrate models into production systems, including interfaces, configuration, deployment, monitoring, and regression safeguards.   Partner with Safety, Systems Engineering, and Product to translate system requirements into concrete ML model requirements, metrics, and validation criteria.   Contribute to verification and validation strategies for the fallback   perception   model, including offline evaluation, simulation, hardware‑in‑the‑loop, and on‑road testing.   Participate in code reviews, promote ML and software engineering best practices, and provide technical mentorship to other engineers.

BS, MS, or PhD in Machine Learning, Robotics, Computer Science, or a related technical field; or equivalent practical experience building ML   perception   systems.   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 (camera, lidar, radar), including data preprocessing, synchronization, and fusion.   Deep   expertise   in modern deep learning for   perception , such as convolutional and transformer‑based architectures for:   2D/3D object detection   Semantic and instance segmentation   Multi‑object tracking and motion prediction   Proficiency   in at least one major ML framework (e.g.,   PyTorch , TensorFlow, JAX) and Python for model development, training, and analysis.   Solid software engineering skills, including experience working in C++ or similar languages in large, collaborative codebases.   Demonstrated ability to define ML metrics, design experiments, and