Senior GPU Memory Architect
NVIDIAJob Title
Senior GPU Memory Architect
Role Summary
Design and evaluate high-performance GPU and system memory architectures with a focus on energy efficiency and performance per watt, millimeter, and dollar. Work within a processor architecture team to develop architecture and microarchitecture features, prototype models, and power/performance analysis to improve system-level PPA.
Collaborate with implementation teams, verification/emulation, silicon partners, and external partners to drive features from concept through silicon validation.
Experience Level
Senior — typically 10+ years of experience in CPU/GPU architecture and memory systems with emphasis on energy efficiency and power/performance analysis.
Responsibilities
Primary responsibilities include architecture design, modeling, analysis, and cross-team collaboration.
- Develop high-performance processor and system architectures, emphasizing memory system and energy efficiency.
- Define microarchitecture features to improve GPU memory-system perf/W, perf/mm, and perf/$.
- Build and enhance architecture prototype models for power and noise analysis.
- Perform performance and power simulations to analyze and improve energy per byte.
- Analyze benchmarks and application workloads to identify optimization opportunities.
- Debug power, performance, and functional issues using high-level models, RTL simulation/emulation, silicon, and systems.
- Collaborate with external partners on system infrastructure and integrations.
Requirements
Must-have skills and experience; preferred items listed separately.
- 10+ years in CPU/GPU architecture or memory-systems design with a focus on energy efficiency.
- Expertise in power analysis and modeling for pipeline-based architectures.
- Familiarity with power analysis tools (examples: Ansys PowerArtist, Synopsys PTPX).
- Proficiency in C and C++, and experience with scripting languages for tooling and analysis.
- Experience debugging across high-level models, RTL, emulation, and silicon.
- Strong quantitative analysis skills for performance and power tradeoffs.
Nice-to-have:
- Experience with hardware description languages such as Verilog or VHDL.
- Experience developing or optimizing algorithms for power efficiency.
- Excellent written and verbal communication for collaboration with internal and external teams.
Education Requirements
Required: Bachelor's degree in Electrical Engineering, Computer Science, or a related technical field — or equivalent practical experience. Preferred: MS or PhD in Electrical Engineering, Computer Science, or related field. No specific certifications were listed in the posting.
About the Company
Company: NVIDIA
Headquarters: Santa Clara, California, USA
NVIDIA is a global leader in accelerated computing, renowned for its innovative solutions in AI and digital twins that transform diverse industries. The company specializes in networking technologies, providing end-to-end InfiniBand and Ethernet solutions for servers and storage that optimize performance and scalability. NVIDIA serves sectors such as high-performance computing, enterprise data centers, and cloud computing, constantly reinventing its products and services to stay ahead in the market.
