Senior Systems Software Engineer, CUDA Driver - Multi-Node and Memory Model
NVIDIAJob Title
Senior Systems Software Engineer, CUDA Driver - Multi-Node and Memory Model
Role Summary
Work on the CUDA Driver team to design and implement memory-model and multi-node scalability features for GPU-accelerated computing. The role focuses on system software, device drivers, and cross-team coordination to enable next-generation AI, scientific computing, and related workloads.
Compensation includes base salary (range provided by level), equity, and benefits.
Experience Level
Senior-level engineer. The posting requests a minimum of 8 years of related development experience.
Responsibilities
Deliver and drive development of CUDA driver features related to memory model and multi-node scalability across multiple teams and platforms.
- Architect, implement, and evangelize enhancements to CUDA’s memory model and multi-node scalability.
- Coordinate and lead development efforts across multiple internal teams.
- Define improvements to CUDA APIs and the programming model.
- Write maintainable, well-tested production code for multiple operating systems.
- Debug and optimize complex system- and driver-level behavior.
Requirements
Must-have technical skills and experience for the role.
- Strong C and C++ programming skills.
- Minimum of 8 years of relevant software development experience.
- Experience driving projects that span multiple teams and stakeholders.
- Experience working with large, complex codebases.
- Familiarity with operating system interfaces for threads, process control, and virtual memory.
- Experience writing and debugging multithreaded programs.
- Good written and presentation skills.
Nice-to-have
- Experience with parallel computing frameworks or PyTorch.
- Experience with low-latency AI inference.
- Understanding of system-level architecture: interconnects, memory hierarchy, interrupts, MMIO.
- Knowledge of memory coherence and consistency models.
- Kernel-mode development experience and experience with Linux or Windows systems software.
Education Requirements
BS or MS 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.
