Principal Perception Engineer, Obstacle Foundation Models - Autonomous Vehicles

What you'll do

• Own the technical vision for 3D obstacle perception to support autonomous driving functionalities.
• Design advanced 3D perception models using multi-camera inputs and sensor fusion techniques.
• Develop efficient, production-grade deep learning models with best practices for training and evaluation.
• Define KPI frameworks to quantify perception performance and improve model accuracy and robustness.
• Lead data strategy for perception, including data collection, annotation, and model-assisted workflows.
• Ensure perception solutions meet safety and deployment requirements across multidisciplinary teams.

What we're looking for

• Over 15 years of hands-on experience developing deep learning-based perception systems for real-world applications.
• Proven technical leadership in designing, implementing, and deploying complex perception solutions at scale.
• Strong proficiency with PyTorch and experience moving models from prototype to production.
• Expertise in data-driven development, including collaboration on data strategy and iterative model improvement.
• Hands-on experience with modern deep learning architectures like CNNs and transformers for autonomous driving.
• Deep understanding of 3D computer vision fundamentals and transformer-based 3D perception pipelines.
• Experience optimizing DNN-based perception pipelines for embedded or real-time platforms using CUDA.