Senior Software Engineer - Autonomous Driving

NVIDIA AI; Santa Clara (CA); On-site; USD 240,000 - 340,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA AI is seeking a senior technical leader to drive the strategy and architecture for optimizing deep neural network inference on NVIDIA automotive platforms. You will define the end-to-end inference stack and lead performance analysis to ensure reliability for autonomous driving software.

Responsibilities include applying model optimization techniques such as quantization, pruning, and distillation, to maximize throughput in embedded automotive environments.

Qualifications

• Over 12 years of experience in systems software or AI/ML infrastructure.
• Strong C/C++ and Python skills with deep familiarity with TensorRT, CUDA, and ML frameworks.
• Experience leading architecture for neural network inference on automotive/platforms.

Responsibilities

• Lead technical strategy and architecture for optimizing deep neural network inference on NVIDIA automotive platforms.
• Drive end-to-end performance analysis for autonomous driving software.
• Develop model optimization techniques to ensure efficient and reliable inference.

Skills

C++

Python

TensorRT

CUDA

Deep Learning Inference

Model Optimization

PyTorch

ONNX

Triton

System Architecture

Quantization

Pruning

Distillation

GPU Performance

Embedded Systems

Real-time Systems

Education

Bachelor's degree in CS or related field

Tools

TensorRT

CUDA Toolkit

Deep Learning Frameworks

Job description

Lead the technical strategy and architecture for optimizing deep neural network inference workloads on NVIDIA automotive platforms. Drive end-to-end performance analysis and develop model optimization techniques to ensure efficient and reliable autonomous driving software.

Requirements: Requires a degree in Computer Science or a related field with over 12 years of experience in systems software or AI/ML infrastructure. Must possess strong C/C++ and Python skills along with deep familiarity with TensorRT, CUDA, and deep learning frameworks.

Key Skills: C++, Python, TensorRT, CUDA, Deep Learning Inference, Model Optimization, PyTorch, ONNX, Triton, System Architecture, Quantization, Pruning, Distillation, GPU Performance, Embedded Systems, Real-time Systems

Benefits: Equity, Benefits