Principal GPU Memory Architect

NVIDIA is hiring a Principal GPU Memory Architect in Santa Clara, United States. It pays $272k-$431k a year and Level rates it ; you can apply on NVIDIA.

Level's read on this job

On Level's scale, this role is Little AI ●○○○: aI is not part of the work.
Level classifies it as a lead role.
Level lists 2,700+ other open roles at NVIDIA.

AI in this role

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 the hardware. Ideal candidates will have a strong track record of understanding and analyzing memory systems architecture to improve performance per watt (perf/W) and performance per millimeter (perf/mm). A broad perspective across the field of computer architecture and depth in the area of power, performance, and area (PPA) analysis is highly desirable. NVIDIA has pioneered programmable GPUs and the CUDA language and is a world leader in high-performance computing technology, with aggressive plans for future processors. This position offers the opportunity to have a real impact in a fast-moving, technology-focused company.

What you will be doing:

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.

What we want to see:

18+ yrs of experience in CPU/GPU architecture, memory systems design with a focus on energy efficiency in the system.
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, etc.
Experience with C, C++, and some scripting languages.

Ways to stand out from the crowd:

MS/PhD in Electrical Engineering, Computer Science, or related field
Experience with hardware design languages such as Verilog or VHDL
Prior experience in developing and optimizing algorithms for power efficiency
Demonstrated ability to innovate and drive continuous improvement in system architecture
Excellent communication skills, both written and verbal, for effective collaboration with internal teams and external partners.

#ArchitectYourFuture

Your base salary will be determined based on your location, experience, and other objective job-related factors. The expected base salary range for this position is 272,000 USD – 431,250 USD.

You will also be eligible for equity and benefits.

Applications for this job will be accepted at least until November 3, 2026.

This posting is for an existing vacancy.

NVIDIA uses AI tools in its recruiting processes.

NVIDIA is committed to fostering an inclusive work environment and proud to be an equal opportunity employer. As we highly value diversity in our current and future employees, we do not discriminate (including in our hiring and promotion practices) on the basis of race, religion, color, national origin, gender, gender expression, sexual orientation, age, marital status, veteran status, disability status or any other characteristic protected by law.

How we rate this

Principal GPU Memory Architect at NVIDIA rates 8 out of 100 for how much of the daily work is AI. That makes it Little AI (AI Level 1 of 4). The level is about AI in the job, not seniority.

Classification

Little AI. AI is not part of the work.

●●●● Builds AI80 to 100
●●●○ Works on AI60 to 79
●●○○ Uses AI40 to 59
●○○○ Little AI0 to 39

Levels come from how often the tools, models and workflows of the role are named in the posting itself. Read the description and count the AI tools, models and workflows it names.