NVIDIA
SoC Product Architect, Memory Ecosystem
$320K–$489K
US, CA, Santa Clara · Full-time · Posted Sep 3, 2026
- Experience
- 18+ years in DRAM / memory subsystem architecture, SoC or memory controller design, or closely related roles in semiconductor or system companies.
- Education
- MS in Electrical Engineering, Computer Engineering, Physics, or related field, or equivalent experience.
About the job
Drives NVIDIA’s external DRAM and non-volatile memory ecosystem, aligning vendor roadmaps and co-optimizing memory solutions with SoC and platform requirements.
What you'll do
- Align memory-vendor product roadmaps with NVIDIA’s SoC and platform roadmaps; communicate performance, power, capacity, form-factor, and reliability requirements.
- Collaborate with vendors to develop DRAM solutions and work with SoC, controller, board, and system teams to co-optimize memory subsystems.
- Represent NVIDIA in vendor reviews and coordinate with sourcing, operations, design, and quality teams on memory technology choices.
What they ask for
- Deep understanding of DRAM and non-volatile memories, including their key tradeoffs.
- Experience working directly with memory vendors on product definition, bring-up, or co-development.
- Background in SoC and system memory subsystems, including memory controllers, PHYs, signal integrity, and power delivery.
- Competitive analysis experience and strong communication, presentation, and cross-functional collaboration skills.
Nice to have
- Experience architecting HBM, GDDR, or high-speed LPDDR solutions for GPUs, AI accelerators, or high-performance SoCs.
- Hands-on experience with advanced packaging involving high-bandwidth memory interfaces.
Pay
320,000 USD - 488,750 USD (base salary)
Tools
DDR, LPDDR, GDDR, HBM, NAND, managed NAND/SSD, CoWoS
AI focus
NVIDIA uses AI tools in its recruiting processes; the role’s AI work is not specified.
Model-written summary · the original posting is authoritative