Senior Radar Perception Engineer for Autonomous Driving

NVIDIA Corporation; California; Sur place; USD 224 000 - 357 000; Plein temps

Résumé du poste

NVIDIA seeks a Senior Radar Perception Engineer to design and productionize radar-based 3D obstacle perception for autonomous driving. You will work on radar pipelines, transformer-based models, and multi-sensor fusion to enable robust BEV scene understanding and tracking.

You will drive architecture, data strategy, and production practices, collaborating with safety, hardware, and software teams to deliver scalable, low-latency perception solutions.

Qualifications

• 12+ years of hands-on experience developing deep learning–based perception, radar signal processing, or closely related systems.
• Strong proficiency in PyTorch and track record of taking models from prototype to production.
• Production-grade software development with Python/C++.

Responsabilités

• Develop and improve radar-based 3D obstacle perception architectures and roadmaps for autonomous driving.
• Investigate advanced deep learning models and large-scale radar data for robust perception.
• Design and implement multi-sensor fusion (camera, radar, lidar) for BEV scene understanding and tracking.
• Drive radar sensor evaluation, layout optimization, and hardware-software integration for safety-critical stacks.
• Prototype, train, and productionize models using data-efficient methods (LoRA, auto-labeling).
• Define KPI frameworks and analyze datasets to improve accuracy and efficiency.

Connaissances

Python

C++

PyTorch

Software Engineering

Cross-functional collaboration

Formation

BS/MS/PhD in CS/EE/Robotics (or related)

Outils

PyTorch

CUDA

C++

Description du poste

NVIDIA seeks a Senior Radar Perception Engineer to design and productionize radar-based 3D obstacle perception for autonomous driving. You will work on radar pipelines, transformer-based models, and multi-sensor fusion to enable robust BEV scene understanding and tracking.

You will drive architecture, data strategy, and production practices, collaborating with safety, hardware, and software teams to deliver scalable, low-latency perception solutions.