Senior GPU Memory Architect

NVIDIA is a global leader and pioneer in accelerated computing. We invent the GPU, which created the market for PC gaming and redefined computer graphics. Our work in deep learning and AI is transforming industries, from healthcare and automotive to finance and entertainment. We are committed to fostering a diverse work environment and are an equal opportunity employer.

Introduction

NVIDIA is seeking a world-class computer architect to contribute to the development of future high-performance computing systems. This role focuses on enhancing the power-constrained performance of hardware, with a strong emphasis on memory systems architecture to improve performance per watt (perf/W) and performance per millimeter (perf/mm).

NVIDIA has pioneered programmable GPUs and the CUDA language, establishing itself as a global leader in high-performance computing technology. This position offers a unique opportunity to make a significant impact within a fast-moving, technology-focused company with aggressive plans for future processors.

Responsibilities

• Develop innovative high-performance processor and system architectures, with a primary focus on memory systems and energy efficiency.
• Design and implement architecture and micro-architecture features to advance the state-of-the-art in GPU memory systems, optimizing across performance per watt (perf/W), performance per millimeter (perf/mm), and performance per dollar (perf/$).
• Develop and enhance architecture prototype models for detailed power and noise analysis.
• Participate in performance and power simulations to analyze, define, and improve energy per byte.
• Conduct in-depth analysis of benchmarks, application workloads, and simulation/emulation results to identify and implement architecture optimizations.
• Debug power, performance, and functional issues using high-level models, RTL simulation and emulation, silicon, and real systems.
• Collaborate with external partners on system infrastructure development.

Requirements

• 10+ years of experience in CPU/GPU architecture and memory systems design, with a strong focus on energy efficiency within system design.
• Bachelor's degree in Electrical Engineering, Computer Science, or a related field (or equivalent practical experience).
• Expertise in power analysis and modeling within pipeline-based architectures.
• Proficiency with power analysis tools such as Ansys Power Artist, Synopsys PTPX, etc.
• Experience with C, C++, and various scripting languages.

Nice to Have

• Master's or Ph.D. in Electrical Engineering, Computer Science, or a related field.
• Experience with hardware design languages, including Verilog or VHDL.
• Proven 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.

Benefits

• Competitive base salary (Level 4: $184,000 - $287,500 USD; Level 5: $224,000 - $356,500 USD).
• Equity options.
• Comprehensive benefits package.

About Company

NVIDIA is a global leader and pioneer in accelerated computing. We invent the GPU, which created the market for PC gaming and redefined computer graphics. Our work in deep learning and AI is transforming industries, from healthcare and automotive to finance and entertainment. We are committed to fostering a diverse work environment and are an equal opportunity employer.

How to Apply

Applications for this job will be accepted at least until May 17, 2026. Please apply directly through the NVIDIA careers portal.