Senior Perception Engineer: 3D Obstacle & Foundation Models

NVIDIA Corporation; Santa Clara, Northern (CA, KY); Hybrid; USD 184,000 - 357,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA Corporation in Santa Clara is seeking a Senior Perception Engineer to design and productize NVIDIA’s next-generation autonomous driving perception stack. You will work on the core 3D obstacle perception pipeline, combining CNNs and transformer-based approaches for multi-camera and multi-sensor fusion.

You will build production-grade DL models, define KPI frameworks, and collaborate across data, safety, and software teams to ensure robust, low-latency performance at scale.

Qualifications

• PhD with 4+ years, MS with 6+ years, or BS with 8+ years in CS/CE or related field.
• Hands-on DL perception experience using PyTorch, production-grade software.
• Data-driven development with data/labeling teams for model improvement.
• Strong Python and/or C++, production-quality software.
• Excellent cross-team collaboration and communication.

Responsibilities

• Design and roadmap for 3D obstacle perception in autonomous driving.
• Develop 3D perception models using multi-camera inputs and multi-sensor fusion.
• Build production-grade DL models with training/evaluation best practices.
• Define KPI frameworks and improve accuracy, robustness, and efficiency.
• Collaborate with safety, systems, and software teams for deployment at scale.

Skills

PyTorch

Python

C++

3D Vision

Communication

Collaboration

Education

PhD with 4+ years or MS with 6+ years or BS with 8+ years in CS/CE

Tools

CUDA

TensorRT

LoRA

Job description

NVIDIA Corporation in Santa Clara is seeking a Senior Perception Engineer to design and productize NVIDIA’s next-generation autonomous driving perception stack. You will work on the core 3D obstacle perception pipeline, combining CNNs and transformer-based approaches for multi-camera and multi-sensor fusion.

You will build production-grade DL models, define KPI frameworks, and collaborate across data, safety, and software teams to ensure robust, low-latency performance at scale.