Principal DRAM Architect – GPU Memory Solutions

NVIDIA • Santa Clara, CA

124d • $272,000 - $425,500

About The Position

NVIDIA is seeking a world-class Principal DRAM Architect to define, drive, and deliver the architecture, roadmap, and implementation of next-generation AI and graphics memory solutions! This role sits at the intersection of I/O design, advanced packaging, and process technology, with a mission to co-optimize DRAM, GPU, and system architectures to achieve unprecedented performance, efficiency, and reliability. As part of NVIDIA’s Memory Architecture team, you will shape the evolution of cutting-edge memory technologies — from TSV stacking and refresh management to advanced reliability and retention schemes — while collaborating closely with leading DRAM vendors and JEDEC working groups to influence global memory standards! Familiarity with HBM, GDDR, and LPDDR is highly valued, enabling broad architectural impact across NVIDIA’s full product portfolio spanning AI accelerators, graphics, data center, and automotive platforms.

Requirements

• MS or PhD in Electrical Engineering, Computer Engineering, Physics (or equivalent experience).
• 15+ years of experience in DRAM or memory system architecture, with at least 5+ years focused on HBM (HBM2/2e/3/3e or next-gen).
• Expertise in HBM architecture: TSV design, die stacking, interposer/CoWoS integration, refresh schemes, ECC/CRC, pseudo-channels, and thermal/power management.
• Proven participation in JEDEC or equivalent standards organizations, contributing to DRAM or HBM specifications.
• Demonstrated ability to influence DRAM vendor roadmaps, negotiate trade-offs, and enable early silicon validation.
• Strong understanding of I/O and PHY design fundamentals — timing, SI/PI, equalization, jitter budgeting.
• Proven experience balancing system-level trade-offs across performance, bandwidth, power, cost, yield, and reliability.
• Exceptional technical leadership and cross-functional communication skills.

Nice To Haves

• Hands-on experience with GDDR6/7 and LPDDR5/6 architectures — including bank management, signaling, power states, and error handling.
• Deep understanding of thermal and mechanical challenges in advanced memory packaging and 3D integration.
• Familiarity with emerging memory technologies (3D DRAM, MRAM, RRAM, or next-gen hybrid memory).
• Publications, patents, or JEDEC leadership roles demonstrating influence on memory architecture and standards.
• Background in high-bandwidth computing platforms — AI, HPC, or graphics accelerators.

Responsibilities

• Architect next-generation DRAM solutions and NVIDIA-specific implementations — including bank and stack structures, refresh mechanisms, retention schemes, ECC/CRC, power management, and reliability optimization.
• Lead innovation in high-speed memory interfaces, with deep expertise in HBM PHYs (wide I/O, TSV signaling, SI/PI, timing margins) and an understanding of GDDR/LPDDR PHY architectures.
• Collaborate across domains on advanced packaging technologies (TSVs, interposers, CoWoS, hybrid bonding, FOWLP) to optimize DRAM–GPU co-packaging for bandwidth, power, thermal performance, and yield.
• Evaluate emerging DRAM process nodes (sub-1x nm, EUV, new capacitor/dielectric materials) and their impact on density, power, retention, and cost.
• Influence industry direction by working with DRAM vendors and actively contributing to JEDEC committees, driving next-generation memory standards and NVIDIA-specific roadmap alignment.
• Model and quantify system-level trade-offs in bandwidth, latency, power, cost, yield, and thermal behavior to guide architectural decisions.
• Mentor engineers, lead technical reviews, and shape NVIDIA’s long-term memory architecture vision.

Benefits

• Competitive salaries
• Generous benefits package
• Equity eligibility

What This Job Offers

• Job Type: Full-time
• Career Level: Principal
• Education Level: Ph.D. or professional degree
• Number of Employees: 5,001-10,000 employees