N

NVIDIA

Designs the chips and software that power AI

Senior Performance Architect - Heterogeneous Workload Optimization

Systems Software EngineeringConfirmed live in the last 24 hours
Full-time

About the Job

Requirements

  • A grasp of the CUDA programming model and experience employing GPU profiling tools such as NVIDIA Nsight Systems and Nsight Compute to address PCIe bottlenecks and kernel stalls.
  • Extensive knowledge of profiling tools such as perf, eBPF, VTune, or Valgrind, along with insight into their internal mechanisms.
  • Experience with distributed compute environments such as Slurm, LSF, or Kubernetes.
  • A BS, MS, or PhD in Computer Science, Electrical Engineering, or a related field, or equivalent experience, with more than 8 years of relevant experience and at least 5 years involved in systems-level performance analysis.

Responsibilities

  • Architect and maintain custom profiling frameworks that provide a unified view of execution across CPU multi-core/multi-socket and GPU multi-node/NVLink environments.
  • Conduct deep-dive benchmarking of EDA applications to characterize memory access patterns, cache hit rates, and instruction-level parallelism.
  • Use GPU profilers to detect GPU-side inefficiencies such as warp divergence, sub-optimal occupancy, and PCIe/NVLink bottlenecks.
  • Develop tools to monitor and attribute high-watermark memory usage in multi-terabyte EDA builds, finding opportunities for data structure compression or smarter memory pooling.
  • Develop predictive models to guide hardware procurement and cloud instance selection based on built gate-count and algorithmic complexity.

Desired Qualifications

  • A passion for meticulous benchmarking and the ability to distill sophisticated performance data into actionable engineering roadmaps.

About the Company

NVIDIA

Designs the chips and software that power AI

NVIDIA designs the chips and software that power artificial intelligence and sells complete data center systems to cloud providers, AI labs, and other businesses, along with GeForce graphics cards for gamers. Its GPUs, chips that perform thousands of calculations at once, became the main hardware for AI after researchers used them to train the AlexNet image-recognition model in 2012. NVIDIA connects many GPUs with its own processors and networking gear into servers and rack-sized computers, and developers program them through its CUDA software. These systems bring in most of its sales, and it also makes chips for cars and robots. Jensen Huang co-founded NVIDIA in 1993, and it is based in Santa Clara, California.

Company size
10,001+
Company stage
IPO
Headquarters
Santa Clara, CA
Founded
1993

Recently Posted Jobs

Explore more opportunities at NVIDIA

See more jobs