Principal Perception Engineer, Obstacle Foundation Models - Autonomous Vehicles

What you'll do

• Own the architecture, technical roadmap, and development of 3D obstacle detection and tracking models using camera and/or fused sensor data.
• Drive model training, evaluation, data strategy, and performance improvements for safety, latency, efficiency, and robustness.
• Provide technical leadership and mentorship, coordinating with cross-functional teams on deployment.

What they ask for

• 15+ years developing deep learning-based perception or closely related systems, including taking models from prototype to production.
• Demonstrated senior/principal-level technical leadership, including end-to-end ownership and cross-team coordination.
• Experience with data-driven development and collaboration with data, labeling, and ground-truth teams.
• Strong Python and/or C++ skills; BS/MS/PhD in Computer Science, Electrical Engineering, or a related field (or equivalent experience).

Nice to have

• Perception deployment experience in autonomous driving or robotics, including embedded or real-time optimization.
• Relevant publications or contributions, 3D computer vision expertise, or CUDA development experience.

Pay

272,000 USD - 431,250 USD (base salary)

Tools

PyTorch, Python, C++, CNN, transformer, LoRA, VLMs, CUDA

AI focus

Develops deep learning-based 3D perception models for autonomous vehicles, including multi-modal and transformer-based approaches, large-scale pretraining, distillation, self-supervised learning, and model-assisted data workflows such as active learning, auto-labeling, and VLMs.