System Software Engineer - GPU

Job Title

System Software Engineer - GPU

Role Summary

Work on low-level system software and test infrastructure for next-generation NVIDIA GPUs. The role focuses on designing and implementing GPU validation, diagnostics, and manufacturing tests in collaboration with architecture, hardware and driver teams.

The team builds foundational tools and automated frameworks to validate hardware features, stress GPU subsystems via compute and graphics APIs, and improve validation efficiency using AI-assisted techniques.

Experience Level

Mid-level — typically requires 5+ years of relevant hardware/software experience.

Responsibilities

Design, implement, and maintain software tools and tests used throughout chip development, validation, and productization.

• Collaborate with architecture, hardware, and driver teams through the product development lifecycle.
• Architect and develop diagnostics and validation capabilities for Data Center and Consumer GPUs.
• Create manufacturing diagnostic tests and validation suites using pre-beta CUDA and Vulkan extensions.
• Use compute and graphics APIs to stress GPU units and system-level flows for coverage and reliability.
• Leverage AI-assisted development tools to accelerate test creation, debugging, and analysis while maintaining code quality.
• Apply AI/ML methods to improve test coverage, failure triage, log analysis, and validation efficiency.
• Identify opportunities for agent-based or automated workflows to increase developer velocity and reliability.

Requirements

Must-have technical skills and experience. Nice-to-have items listed separately.

• Must-have: Strong C/C++ programming skills; deep systems software knowledge with emphasis on OS fundamentals.
• Must-have: Thorough knowledge of GPU concepts, algorithms, and current-generation hardware architecture; strong debugging and problem-solving skills.
• Must-have: Experience working close to hardware and on large system software code bases; ability to self-manage and collaborate across teams.
• Must-have: Experience using AI-assisted software development workflows to improve developer velocity and quality.
• Nice-to-have: Background in Parallel Computing, PCIe, NVLink, Infiniband, Ethernet, or other server interconnects.
• Nice-to-have: Prior experience with CUDA, Vulkan, or developing validation/diagnostic frameworks for GPUs.

Education Requirements

BS or MS in Electrical Engineering, Computer Engineering, Computer Science, or a related technical field — or equivalent practical experience.

About the Company

Company: NVIDIA

Headquarters: Santa Clara, California, USA

NVIDIA is a global leader in accelerated computing, renowned for its innovative solutions in AI and digital twins that transform diverse industries. The company specializes in networking technologies, providing end-to-end InfiniBand and Ethernet solutions for servers and storage that optimize performance and scalability. NVIDIA serves sectors such as high-performance computing, enterprise data centers, and cloud computing, constantly reinventing its products and services to stay ahead in the market.