Principal GPU Memory Architect
$272k - $431k • US, CA, Santa Clara
Posted 12d ago
About the job
NVIDIA is seeking a world-class computer architect to contribute to the development of future high-performance computing systems, with a focus on enhancing the power-constrained performance of hardware. The ideal candidate will have a strong track record of understanding and analyzing memory systems architecture to improve performance per watt and performance per millimeter. A broad perspective across computer architecture and depth in power, performance, and area (PPA) analysis is highly desirable. This position offers the opportunity to have a real impact in a fast-moving, technology-focused company.
Responsibilities
- Develop innovative high-performance processor and system architectures, focusing on the memory system and energy efficiency.
- Develop architecture and micro-architecture features to improve the state-of-the-art in GPU memory systems, optimizing along the axes of perf/W, perf/mm, and perf/$
- Develop and enhance architecture prototype models for power and noise analysis.
- Participate in performance and power simulation of features to analyze, define, and improve energy per byte.
- Analyze benchmarks, application workloads, and performance/power simulation and emulation results to identify areas for architecture optimizations.
- Debug power, performance, and functional issues with high-level models, RTL simulation and emulation, silicon, and systems.
- Collaborate with outside partners on system infrastructure.
Requirements
- 18+ years of experience in CPU/GPU architecture, memory systems design with a focus on energy efficiency.
- Bachelors in Electrical Engineering, Computer Science, or related field (or equivalent experience).
- Expertise in power analysis and modeling in pipeline-based architectures.
- Good understanding of power analysis tools like Ansys Power Artist, Synopsys PTPX.
- Experience with C, C++, and some scripting languages.
Benefits
- Equity
- Benefits