Senior 3D Perception Engineer (Autonomous Driving)

NVIDIA; New York (NY); On-site; USD 184,000 - 357,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA seeks a Senior Perception Engineer to design and productize the autonomous driving perception stack. You will work on core 3D obstacle perception, leveraging CNNs and transformers, and stay hands-on with models across multi-camera inputs and multi-sensor fusion.

You will collaborate with safety, systems, and software teams to ensure latency, robustness, and scalability, and contribute to data strategy, labeling quality, and model-in-the-loop tooling. Equity and benefits apply.

Qualifications

• PhD/MS/BS with years of relevant experience in computer science, computer engineering, or related field.
• Hands-on DL perception systems experience and production-grade model deployment.
• Data-driven development with collaboration with labeling and ground-truth teams.
• Strong Python/C++ programming and experience with reliable, high-performance software.
• Excellent communication and cross-disciplinary collaboration.

Responsibilities

• Design and build 3D obstacle perception models with multi-camera and multi-sensor fusion.
• Develop production-grade DL models, run experiments, and optimize for latency and efficiency.
• Shape KPI frameworks and analyze large datasets to improve accuracy and robustness.
• Collaborate with safety, systems, and software teams for scalable deployment.
• Contribute to data strategy, labeling requirements, and model-in-the-loop tooling.
• Explore BEV and transformer-based 3D perception architectures and VLMs where helpful.

Skills

Deep learning

3D perception

Vision transformers

Multi-sensor fusion

Python

C++

PyTorch

Data-driven development

Communication

Education

PhD in CS/EE or related field

MS in CS/EE or related field

BS or equivalent with extensive experience

Tools

PyTorch

CUDA

C++

Python

Job description

NVIDIA seeks a Senior Perception Engineer to design and productize the autonomous driving perception stack. You will work on core 3D obstacle perception, leveraging CNNs and transformers, and stay hands-on with models across multi-camera inputs and multi-sensor fusion.

You will collaborate with safety, systems, and software teams to ensure latency, robustness, and scalability, and contribute to data strategy, labeling quality, and model-in-the-loop tooling. Equity and benefits apply.