NVIDIA
Senior CPU Performance Architect
$224K–$431K
US, CA, Santa Clara +2 · Senior · Full-time · Posted Apr 8, 2026
- Location
- US, CA, Santa Clara
US, TX, Austin
US, OR, Hillsboro - Experience
- 12+ years of relevant experience.
- Education
- BS/MS in Electrical Engineering, Computer Science, Computer Engineering, or equivalent experience.
About the job
Develop and analyze CPU performance across workloads and systems, using findings to improve future CPU and system designs.
What you'll do
- Bring up workloads and analyze or project performance on silicon and full-system simulators.
- Analyze performance bottlenecks in multi-core, multi-socket CPU, and CPU/GPU systems; reduce real-world use cases to directed tests.
- Benchmark NVIDIA CPUs against competitors and work with architects to recommend software or hardware improvements.
What they ask for
- BS/MS in Electrical Engineering, Computer Science, Computer Engineering, or equivalent experience.
- Experience with CPU workloads and performance analysis.
- Knowledge of performance test development and benchmarking for CPU and I/O.
- Deep knowledge of CPU microarchitecture and system architecture.
Nice to have
- ARM instruction set architecture (ISA) experience (preferable but not required).
- PhD or research experience; GPU driver experience; GPU-accelerated workload modeling; or performance optimization of AI frameworks such as PyTorch.
Pay
224,000 USD - 356,500 USD base salary (Level 5); 272,000 USD - 431,250 USD base salary (Level 6)
Tools
ARM instruction set architecture (ISA), PyTorch
AI focus
Studies AI/deep-learning and GPU-accelerated workloads and may optimize AI frameworks such as PyTorch.
Model-written summary · the original posting is authoritative