NVIDIA
Senior Performance Architect - Heterogeneous Workload Optimization
$184K–$356K
US, CA, Santa Clara +3 · Senior · Full-time · Posted Sep 6, 2026
- Location
- US, CA, Santa Clara
US, MA, Westford
US, TX, Austin
US, NC, Durham - Experience
- More than 8+ years of relevant experience, including at least 5 years in systems-level performance analysis.
- Education
- BS, MS, or PhD in Computer Science, Electrical Engineering, or a related field (or equivalent experience).
About the job
Build profiling infrastructure and optimize CPU–GPU performance for EDA workloads, including benchmarking, memory analysis, and performance modeling.
What you'll do
- Architect and maintain profiling frameworks across CPU and GPU environments; benchmark EDA applications and analyze performance bottlenecks.
- Use GPU profilers to identify inefficiencies and develop tools to track memory use and improve memory management.
- Build predictive models to inform hardware procurement and cloud instance selection.
What they ask for
- Knowledge of the CUDA programming model and experience with GPU profiling tools such as NVIDIA Nsight Systems/Compute.
- Extensive knowledge of profiling tools such as perf, eBPF, VTune, or Valgrind, including their internal mechanisms.
- Experience with distributed compute environments such as Slurm, LSF, or Kubernetes.
- BS, MS, or PhD in Computer Science, Electrical Engineering, or a related field (or equivalent experience).
Pay
184,000 USD - 287,500 USD base salary; 224,000 USD - 356,500 USD base salary
Tools
CUDA, NVIDIA Nsight Systems/Compute, perf, eBPF, VTune, Valgrind, Slurm, LSF
AI focus
NVIDIA states that it uses AI tools in its recruiting processes; the role description does not specify AI-related job duties.
Model-written summary · the original posting is authoritative