Senior Engineer - Perception Modeling

Role overview A senior perception engineering position on an autonomous vehicle program developing self-driving technology. The role focuses on advancing multi-modal perception through foundation models, synthetic data, and knowledge distillation, working alongside ML engineers and research scientists to deploy robust onboard perception systems.

Responsibilities - Lead the architecture and development of large-scale multi-modal foundation perception systems that generalize across vehicle generations. - Architect and scale synthetic data generation and sensor simulation capabilities for long-tail edge cases, off-log scenarios, and closed-loop evaluation. - Drive knowledge transfer from large teacher or foundation models into efficient onboard real-time perception models using distillation and post-training techniques. - Productionize and deploy perception solutions onto autonomous vehicle fleets. - Provide technical leadership and mentorship to senior and mid-level engineers.

Requirements - 3+ years of experience in machine learning, computer science, robotics, or a closely related field. - Master's or PhD in machine learning, computer science, robotics, applied mathematics, statistics, physics, or a related discipline, or equivalent industry experience. - Strong understanding of core machine learning and deep learning algorithms. - Hands-on experience designing, training, and analyzing neural networks for tasks such as object detection, semantic or instance segmentation, classification, sensor fusion, multi-task learning, multi-object tracking, or end-to-end perception. - Proficiency with deep learning frameworks such as TensorFlow or PyTorch, and fluency in Python including scientific computing libraries and bindings development. - Solid software engineering fundamentals across design, source control, build, code review, and testing, plus strong communication, interpersonal skills, and prior mentoring experience.

Nice to have - Track record designing, training, or fine-tuning foundation models (for example vision-language or multimodal transformers) for autonomous driving or robotic perception. - Deep expertise in world models, generative video or lidar prediction, scene synthesis, and sensor simulation for closed-loop evaluation. - Strong knowledge distillation and model compression experience for edge deployment. - Synthetic data generation and automated multi-modal labeling experience, and publications in top computer vision or machine learning venues.

Benefits and work setup Salary range of $172,000 to $229,000 USD, with potential bonus or equity. Benefits include medical, dental, vision, 401(k) with company match, health savings accounts, life insurance, and pet insurance.