Senior System Software Engineer, Performance - CUDA Driver

at Nvidia

📍 Santa Clara, United States

USD 184,000-356,500 per year

SENIOR

✅ Hybrid

Tech Stack
Tag name is followed by "@" symbol and proficiency level value. About proficiency levels:

1-2 — basic awareness. Minimal hands-on experience, and a rudimentary understanding of the technology's purpose;

3-6 — daily use. Comfortable and regular usage, capable of handling common tasks and challenges related to the technology;

7-9 — you are an expert, you can teach others, you know all the pitfalls and tricks;

10 — exceptional knowledge, comprehensive understanding, and adeptness in all aspects of the technology, including advanced problem-solving. Think twice before claiming or demanding such level.

API CUDA Communication @ 6 Debugging @ 4 Deep Learning GPU Linux @ 4 macOS @ 4

Details

Work on the CUDA driver and runtime, core components of NVIDIA's platform for accelerating general-purpose computation on GPUs. The team analyzes application performance, investigates software and hardware bottlenecks, and delivers features and improvements for workloads including deep learning, scientific computation, self-driving cars, video games, and virtual reality.

CUDA defines a unified programming model across system configurations and hardware capabilities. The CUDA driver interacts with GPU hardware, kernel-mode drivers, and operating systems.

Responsibilities

Evangelize, architect, and implement new features.
Oversee and drive development efforts across multiple teams.
Analyze full-stack performance across application-level software, libraries, system software, kernel software, and hardware.
Define forward-looking improvements to CUDA APIs and the programming model.
Create novel system software optimizations.
Write effective, maintainable, and well-tested code.
Develop code for multiple operating systems.
Investigate complex performance problems and deliver robust solutions that accelerate applications.
Collaborate with peers across NVIDIA to shape the future direction of CUDA.

Requirements

Bachelor's or master's degree in Computer Science, Electrical Engineering, or equivalent experience.
7+ years of related development experience.
Strong C programming skills.
Experience working with large codebases.
A track record of debugging performance problems in complex environments involving software and hardware components.
Experience with operating system interfaces for threads, process control, and virtual memory.
Experience writing and debugging multithreaded programs.
Deep understanding of technology and passion for the work.
Strong collaborative and interpersonal skills, including the ability to guide and influence effectively within a dynamic matrix environment.
Good written communication skills.

Preferred Qualifications

Understanding of system-level architecture, including interconnects, memory hierarchy, interrupts, and memory-mapped I/O.
Experience tuning the performance of device drivers or low-level system software.
Experience optimizing performance across CPU architectures such as x86, POWER, and ARM.
Knowledge of memory coherence and consistency models.
Experience with Windows, Linux, or macOS driver development.

Compensation and Benefits

Base salary for Level 4: USD 184,000–287,500 per year.
Base salary for Level 5: USD 224,000–356,500 per year.
Eligible for equity and benefits.
Applications will be accepted at least until July 28, 2026.
NVIDIA is an equal opportunity employer committed to an inclusive work environment.