Senior CUDA Driver Performance Engineer

NVIDIA Corporation; Santa Clara (CA); Hybrid; USD 184,000 - 288,000; Full time

Job summary

NVIDIA Corporation in California seeks senior systems software engineers to accelerate the CUDA Driver and related systems software across CPU, interconnects, and GPUs. You will trace workloads, design production features, and ship validated optimizations for current and future NVIDIA GPUs.

You will lead cross-layer investigations, mentor engineers, and influence performance direction while collaborating with CUDA software, hardware, frameworks, applications, product, and customer-facing teams.

Qualifications

• 7+ years of relevant systems-software development experience.
• Strong production C/C++ systems-programming in a complex codebase.
• Solid OS and concurrency foundations: threads, synchronization, processes, virtual memory.
• Strong computer architecture foundations and data movement across interconnects.

Responsibilities

• Develop and ship performance-centric CUDA Driver features and programming-model capabilities.
• Diagnose complex performance problems via workload analysis and modeling.
• Optimize CUDA primitives, memory movement, CPU-GPU coordination, and interconnects.
• Set performance goals for current and future platforms and drive readiness.
• Translate workload evidence into CUDA API, programming model, and architecture recommendations.
• Set subsystem performance direction and mentor engineers.
• Influence technical decisions with performance data and code reviews.

Skills

C/C++ systems programming

Operating systems concepts

Concurrency and synchronization

Performance optimization

Education

BS/MS/PhD in Computer Science, Computer Engineering, Electrical Engineering or equivalent

Tools

Python

Job description

NVIDIA Corporation in California seeks senior systems software engineers to accelerate the CUDA Driver and related systems software across CPU, interconnects, and GPUs. You will trace workloads, design production features, and ship validated optimizations for current and future NVIDIA GPUs.

You will lead cross-layer investigations, mentor engineers, and influence performance direction while collaborating with CUDA software, hardware, frameworks, applications, product, and customer-facing teams.