Senior System Software Engineer, Performance - CUDA Driver
$184k - $357k • US, CA, Santa Clara
Posted 5d ago
Job Location
US, CA, Santa Clara
Tech Stack
Remote Work Policy
On-site
Categories
Machine Learning Engineer
About the job
We are seeking senior systems software engineers to enhance the performance, efficiency, and readiness of the CUDA Driver for next-generation accelerated computing. This role involves developing performance-critical CUDA Driver features and systems software improvements to maximize the potential of NVIDIA GPUs for AI, deep learning, HPC, and other CUDA-powered applications. You will tackle complex performance challenges at the intersection of systems software, CPUs, interconnects, and GPUs, tracing issues from real workloads through the entire stack, designing and shipping production features, and delivering validated optimizations for current and emerging platforms. This position offers the opportunity to combine hands-on engineering with broad technical influence, collaborating with various CUDA software, hardware architecture, frameworks, applications, product, and customer-facing teams. You will lead cross-layer investigations, mentor engineers, and help define performance direction, shaping both current GPU utilization and future CUDA software and GPU architectures.
Responsibilities
- Develop and ship performance-centric CUDA Driver features and programming-model capabilities from design through validation.
- Diagnose complex performance problems through workload analysis, measurement, modeling, and cross-layer root-cause isolation.
- Optimize critical CUDA primitives, memory management, CPU–GPU coordination, and interconnect paths for latency, throughput, bandwidth, efficiency, and scalability.
- Establish performance goals for current and future platforms, characterize new platforms, close software and hardware gaps, and drive performance readiness.
- Translate workload and platform evidence into recommendations for CUDA API, programming model, system software, and future GPU architecture.
- Set subsystem performance direction and mentor engineers on complex systems and performance challenges.
- Influence technical decisions with performance evidence and tradeoffs, and strengthen implementations through rigorous reviews.
Requirements
- BS, MS, or PhD in Computer Science, Computer Engineering, Electrical Engineering, or related field, or equivalent practical experience, with at least 7+ years of relevant systems-software development experience.
- Strong production C/C++ systems-programming experience, including delivery of substantial features, optimizations, or fixes in a complex codebase.
- Strong operating systems and concurrency foundations (threads, synchronization, processes, virtual memory, user/kernel interactions).
- Strong computer architecture foundations (processors, memory hierarchy, caching, data movement, system interconnects).
- Demonstrated success in improving real software performance through measurement, bottleneck identification, optimization, and profiling.
- 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 if accompanied by deep systems software, operating systems, computer architecture, and performance-engineering foundations.
Benefits
- Equity
- Benefits