Senior System Software Engineer, Performance - CUDA Driver
NVIDIAJob Title
Senior System Software Engineer, Performance - CUDA Driver
Role Summary
Work on the CUDA driver and runtime to analyze application performance, identify software and hardware bottlenecks, and deliver features and optimizations that improve GPU-accelerated computation across workloads such as deep learning, scientific computing, autonomous vehicles, and gaming.
The team spans system software, kernel drivers, libraries, and hardware interfaces; you will collaborate across teams to design, implement, and validate performance improvements.
Experience Level
Senior — typically 7+ years of related development experience.
Responsibilities
Deliver performance improvements and new system-software features for the CUDA platform.
- Evangelize, architect, and implement new features in the CUDA driver and runtime.
- Lead and coordinate development across multiple teams.
- Profile and analyze full-stack performance from application level through libraries, system software, kernel software, and hardware.
- Define improvements to CUDA APIs and the programming model.
- Design and implement system-software optimizations for low-level performance.
- Write maintainable, well-tested C code and debug in large codebases.
- Develop and debug code across multiple operating systems and platforms.
Requirements
Core technical qualifications and skills required, plus desirable skills that improve candidacy.
Must-have- 7+ years of related development experience working on system or performance-sensitive software.
- Strong C programming skills and experience with large codebases.
- Proven track record of debugging and resolving performance problems in environments with both software and hardware components.
- Experience with operating system interfaces for threads, process control, and virtual memory.
- Experience writing and debugging multithreaded programs.
- Strong collaboration and communication skills; ability to influence across a matrix organization.
- Understanding of system-level architecture (interconnects, memory hierarchy, interrupts, memory-mapped I/O).
- Experience tuning device drivers or low-level system software for performance.
- Performance optimizations across multiple CPU architectures (x86, POWER, ARM).
- Knowledge of memory coherence and consistency models.
- Experience with driver development on Windows, Linux, or macOS.
Education Requirements
BS or MS in Computer Science, Electrical Engineering, 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.
