System Software Engineer, Performance - CUDA Driver

NVIDIA•Santa Clara, CA

8d•$124,000 - $195,500

About The Position

NVIDIA is seeking a systems software engineer to develop performance-centric features and optimizations in the CUDA driver and runtime. The role involves designing, implementing, validating, and shipping production C/C++ software; analyzing workloads across application, operating-system, CPU, interconnect, and GPU boundaries; and bringing up new platforms. The work targets improvements to kernel launch, synchronization, memory management and movement, CPU–GPU coordination, and interconnect use, with a focus on latency, throughput, bandwidth, efficiency, and scalability. The engineer will own complex performance problems end to end, from understanding workloads and forming hypotheses to measuring behavior, identifying root causes, implementing production solutions, and validating application-level impact. The role also translates workload and platform evidence into CUDA API and programming-model improvements, software direction, and recommendations for future hardware. It includes collaboration across software, hardware, product, and customer-facing teams, and may involve leading subsystem direction, mentoring engineers, and shaping hardware/software decisions for future product generations.

Requirements

BS, MS, or PhD in Computer Science, Computer Engineering, Electrical Engineering, or a related field, or equivalent practical experience.
At least 2 years of relevant systems-software development experience.
Strong production C/C++ systems-programming experience, including delivery of substantial features, optimizations, or production fixes in a complex codebase.
Strong operating-systems and concurrency foundations, including threads, synchronization, processes, virtual memory, and user/kernel interactions.
Strong computer-architecture foundations, including processors, memory hierarchy, caching and coherence, data movement, and system interconnects.
Demonstrated ability to improve real software performance by measuring behavior, identifying the limiting mechanism, implementing an effective solution, and quantitatively validating the result.
Sound technical judgment, ownership of ambiguous problems, and clear communication across organizational and disciplinary boundaries.
Direct CUDA or GPU experience is valuable but not required when accompanied by deep systems-software, operating-systems, computer-architecture, and performance-engineering foundations.

Nice To Haves

Experience developing GPU or accelerator drivers, runtimes, kernel software, firmware, compilers, or other performance-critical low-level systems.
Experience with pre-silicon analysis, platform bring-up, performance modeling, or hardware/software co-design.
Systems-level performance experience with AI/DL, HPC, graphics, automotive, robotics, or similarly demanding workloads.
Evidence of technical inventions, such as software-performance patents, novel production designs, or measurement-backed recommendations that influenced a hardware revision or future architecture.
Python or another scripting language used for focused experimentation, data analysis, or visualization.

Responsibilities

Design, implement, validate, and ship performance-centric features and programming-model capabilities in the CUDA driver and runtime using maintainable, well-tested production C/C++.
Optimize kernel launch, synchronization, memory management and movement, CPU–GPU coordination, and system interconnect paths for latency, throughput, bandwidth, efficiency, and scalability.
Own performance investigations end to end: understand workloads, form hypotheses, create measurements and models, isolate root causes across software and hardware, implement solutions, and validate application-level impact.
Establish performance expectations for current and future platforms, characterize new silicon, close software and hardware gaps, and drive performance readiness through product release.
Translate workload and platform evidence into CUDA API and programming-model improvements, systems-software direction, and measurement-backed recommendations for future hardware architecture and implementation.
Collaborate with application, library, framework, operating-system, driver, runtime, firmware, GPU architecture, silicon, product, and customer-facing teams.
Communicate findings clearly and contribute to engineering quality through design and code reviews.
Lead complex feature development and cross-layer investigations, define performance requirements and technical direction for major subsystems, mentor engineers, and shape hardware/software decisions for future product generations.