CUDA System Software Engineer - Performance & GPU Kernel

NVIDIA AI; Santa Clara (CA); On-site; USD 180,000 - 240,000; Full time

Benefits offered by this job

Equity

Job summary

NVIDIA AI in Santa Clara seeks a systems software engineer to design and implement performance-centric features for the CUDA driver and runtime using C/C++. You will analyze critical paths across software and hardware to boost latency, throughput, and scalability.

The role requires a CS degree and at least two years in systems software, with strong C/C++, OS, and architecture skills. Collaboration across teams to optimize GPU drivers and kernel code is essential.

Qualifications

• Requires a degree in Computer Science or a related field with at least 2 years of systems-software development experience.
• Strong foundations in C/C++, operating systems, and computer architecture with a proven track record of improving software performance.

Responsibilities

• Design and implement performance-centric features and optimizations within the CUDA driver and runtime using C/C++.
• Analyze and optimize critical execution paths across software and hardware boundaries to improve latency, throughput, and scalability.

Skills

C++

CUDA

Operating Systems

Computer Architecture

Performance Engineering

Concurrency

Virtual Memory

GPU Drivers

Kernel Development

Python

System Interconnects

Memory Management

Low-level Systems Programming

Performance Modeling

Hardware/Software Co-design

Education

Bachelor's degree in Computer Science or related field

Job description

NVIDIA AI in Santa Clara seeks a systems software engineer to design and implement performance-centric features for the CUDA driver and runtime using C/C++. You will analyze critical paths across software and hardware to boost latency, throughput, and scalability.

The role requires a CS degree and at least two years in systems software, with strong C/C++, OS, and architecture skills. Collaboration across teams to optimize GPU drivers and kernel code is essential.