Staff Software Engineer, Deep Learning Acceleration

What you'll do

• Analyze and optimize deep learning network performance, including GPU memory use, latency, and throughput.
• Improve software architecture and deploy deep learning models on vehicles and in data centers; troubleshoot bottlenecks using profiling and roofline models.
• Collaborate with engineers and researchers to improve self-driving technology efficiency and reliability.

What they ask for

• At least 5 years of professional software engineering experience.
• BS, MS, or PhD in Computer Science or a related field.
• Strong programming skills in CUDA, C++, and Python, with extensive high-performance computing and parallel programming experience.
• Hands-on framework-level DL/ML workload optimization experience and proficiency with performance analysis tools such as NVIDIA Nsight Systems and Nsight Compute.

Nice to have

• Hands-on experience in motion planning, robotics, autonomous systems, systems software, or computer vision.
• Experience with TensorRT, OpenAI Triton, Mojo, or other inference acceleration tools.

Pay

$189,000 - $274,000 per year (base salary; Mountain View, CA and San Francisco, CA); $171,000 - $247,000 per year (base salary; Pittsburgh, PA)

Tools

CUDA, C++, Python, NVIDIA Nsight Systems, Nsight Compute, PyTorch, TensorFlow, TensorRT

AI focus

Accelerate and optimize deep learning models for autonomous vehicle deployment and large-scale data-center training.