Senior GPU Memory Architect
NVIDIAJob Title
Senior GPU Memory Architect
Role Summary
Senior architect on the GPU memory architecture team responsible for designing and optimizing GPU memory systems and memory management across performance, power, area, complexity, and implementation effort.
The role works with cross-functional silicon, RTL, and software teams to produce specifications, performance models, and experiments that guide microarchitecture and implementation decisions.
Experience Level
Senior — typically requires 6+ years of relevant work experience in GPU or CPU architecture, with a focus on memory caching and interconnects.
Responsibilities
You will define and validate GPU memory architecture and microarchitecture, build models and experiments, and work with partners to deliver production-ready designs.
- Develop architecture and micro-architecture to advance GPU memory systems and memory management, optimizing performance, power, complexity, area, and schedule.
- Participate in performance simulation and implement/maintain high-level functional and performance models.
- Analyze benchmarks and application workloads to identify opportunities for microarchitecture optimization.
- Design and run experiments, present results, and propose mechanisms to improve memory access efficiency.
- Create architectural specifications and customer-facing documentation; coordinate software interface and industry partner requirements.
- Debug performance and functional issues using high-level models, RTL simulation, and silicon bring-up.
Requirements
Key qualifications and skills for successful candidates.
- Must-have: 6+ years of experience in GPU or CPU architecture and development, specifically in memory caching and interconnects.
- Must-have: Hands-on experience with performance modeling, simulation, and analyzing workload-driven performance results.
- Must-have: Strong communication and interpersonal skills and experience working in dynamic, product-oriented, distributed teams.
- Must-have: Demonstrated ability to mentor junior engineers and interns.
- Nice-to-have: Experience with hardware memory management units (MMU), prefetching, or memory subsystems.
- Nice-to-have: Practical experience with multi-core systems and memory coherency.
Education Requirements
Master's degree or equivalent practical experience in Electrical Engineering, Computer Science, Computer Engineering, or a related technical field. A PhD in computer architecture is a plus. "Or equivalent experience" language is acceptable.
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.
