Senior Perception Engineer, Obstacle Foundation Models - Autonomous Vehicles
Core
Design and productize NVIDIA's next-generation autonomous driving perception stack, focusing on the core 3D obstacle perception pipeline using multi-modal sensor fusion and transformer-based architectures.
Role type
Senior IC machine-learning engineer (autonomous driving perception)
Builds
3D obstacle detection and tracking models for end-to-end autonomous driving functionalities
Domain
Autonomous vehicles / Computer vision / Deep learning
Deliverable
production ML models
Required skills
Deep learning model development, 3D computer vision, multi-modal sensor fusion, transformer architectures, Python, C++, CUDA, data strategy, model evaluation
Preferred skills
BEV perception, vision-language models (VLMs), large-scale pretraining, parameter-efficient fine-tuning (LoRA), embedded/real-time platform optimization, academic publication record
Technologies
PyTorch, CUDA, CNNs, Transformers, multi-camera systems, radar, lidar
Responsibilities
Develop technical design and roadmap for 3D obstacle perception; Design and implement advanced 3D perception models using multi-sensor fusion; Build efficient production-grade deep learning models; Define and maintain KPI frameworks for perception performance; Contribute to data strategy including labeling requirements and model-assisted workflows; Collaborate with safety and systems teams to ensure deployment readiness
Seniority
Senior, hands-on IC
