Principal System Software Engineer - CUDA Driver
NVIDIAJob Title
Principal System Software Engineer - CUDA Driver
Role Summary
Work on the CUDA driver, a core system software component that interfaces with GPU hardware, kernel-mode drivers, and operating systems to enable high-performance general-purpose computation on NVIDIA GPUs.
The team implements new CUDA features, improves performance and precision modeling, and collaborates with hardware architects and cross-functional teams to define the programming model and runtime behavior.
Experience Level
Senior-level engineer. The role requests 15+ years of relevant systems software development experience.
Responsibilities
Provide technical leadership and deliver production-quality system software for the CUDA platform.
- Evangelize, architect, and implement new CUDA features and platform capabilities.
- Oversee and drive development efforts across multiple engineering teams.
- Collaborate with hardware architecture teams to expose and support HW features in software.
- Define improvements to CUDA APIs and the programming model.
- Design and maintain performance and precision modeling and validation.
- Write maintainable, well-tested code and develop across multiple operating systems.
Requirements
Core technical qualifications and professional skills required; additional items are desirable.
- 15+ years of systems software development experience working on complex software stacks.
- Strong C programming skills; ability to produce clear, maintainable code and tests.
- Experience designing, debugging, and maintaining layered system software.
- Familiarity with operating system interfaces for threads, process control, and virtual memory.
- Experience with HW/SW co-design and performance modeling using emulation or simulation.
- Proven ability to work collaboratively and influence across a matrix organization; strong written and verbal communication.
Nice-to-have:
- Understanding of system-level architecture: interconnects, memory hierarchy, interrupts, and MMIO.
- Experience designing and implementing drivers for hardware acceleration engines and associated verification testplans.
- Knowledge of CPU/GPU architectures, memory coherence/consistency models, and kernel-mode development.
- Familiarity with C++.
Education Requirements
Bachelor's or Master's degree in Computer Science, Electrical Engineering, or a related 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.
