Senior Software Engineer - CUDA Driver at NVIDIA

Department: Engineer, Sys SW

Compensation

$152,000 – $287,500/yr

Setup: On-site
Location: California
Type: Full-time
Level: senior
Posted: Aug 31, 2026

Description

NVIDIA is hiring a senior software engineer to develop and advance CUDA driver software, including kernel-mode components, compilers, networking software, APIs, and programming models. The role involves system-level architecture, performance and precision modeling, cross-team coordination, and code development across multiple operating systems. Candidates need a relevant bachelor's or master's degree, at least five years of systems software experience, strong C programming skills, and experience with operating-system interfaces, HW/SW co-design, and parallel computing. The base salary is 152,000–241,500 USD for Level 3 and 184,000–287,500 USD for Level 4, with equity and benefits.

Required Skills

C programming
Operating systems
HW/SW co-design
Parallel computing
CUDA programming
Kernel-mode development
Performance modeling

Additional Information

Minimum Education: Bachelor of Science or Master of Science degree in Computer Science, Electrical Engineering, or a related field, or equivalent experience
Required Previous Experiences: 5+ years of relevant systems software development experience
Experience designing, debugging, and maintaining complex software stacks
Experience with operating-system interfaces for threads, process control, and virtual memory
Experience with HW/SW co-design, performance modeling, and software programming-model development
Preferred Qualifications: Experience with kernel scheduling, task runtimes, kernel-mode development, and Linux systems software
Strong background in parallel computing, preferably with CUDA programs or CUDA-based libraries
Knowledge of memory coherence and consistency models in concurrent and parallel systems
Experience maintaining and extending programming models or higher-level language support for Linux or similar environments
Familiarity with distributed training and inference patterns and deep learning frameworks