Senior Distinguished Custom Memory Architect Engineer

About Marvell

Marvell’s semiconductor solutions are the essential building blocks of the data infrastructure that connects our world. Across enterprise, cloud and AI, automotive, and carrier architectures, our innovative technology is enabling new possibilities.

At Marvell, you can affect the arc of individual lives, lift the trajectory of entire industries, and fuel the transformative potential of tomorrow. For those looking to make their mark on purposeful and enduring innovation, above and beyond fleeting trends, Marvell is a place to thrive, learn, and lead.

Your Team, Your Impact

Marvell is looking for a driven and innovative Senior Distinguished Custom Memory Architect Engineer to push the boundaries on next generation memory architectures of Marvell’s leading datacenter product roadmap. That includes among others pathfinding work to explore new memory technologies and work closely with peer architecture teams, memory vendors, standard organizations, and customers to define and design next generation AI leading SoCs.

What You Can Expect

As a Senior Distinguished Memory Architect Engineer in the CTO Office organization, you’ll be responsible for:

• Defining next generation custom and standard based memory solutions which provide differentiating value to datacenter SoC products.
• Researching state-of-the-art memory technologies, close collaboration with SoC architects, and pathfinding memory architectures and solutions.
• Weigh technical tradeoffs affecting performance, power, area, reliability, and yield, and to effectively communicate value propositions and risks to organizational leaders.
• Work across peer SoC architecture, system, and design team, leveraging their expertise into pathfinding new IP solutions across a broad range of market applications.
• Work with limited direction, have keen attention to detail, and be able to provide crisp status of program progress, issues, and risks to the management team.
• Leading the development of performance models and features to enhance memory system performance and efficiency.
• Responsible for performance analysis, micro-benchmarking, workload characterization, competitive analysis, bottleneck identification, and optimization.
• Communicate, propose, and implement solutions to processor and system performance issues.
• Work with relevant standard organizations, vendors, peer companies and customers to drive memory innovations.
• Drive initiatives into standard organizations representing Marvell.

What We're Looking For

• Deep familiarity and understanding of memory systems, memory component technologies, DDR, HBM, memory controller architecture, various DIMM types and caching architectures.
• Prior experience with HBM and DDR4/5 technologies is a must requirement.
• A proven and successful track record of shipping memory system products at scale for complex SoCs / processors / GPUs.
• Hands on experience in performance model development, able to develop exceptionally accurate models for tradeoff analysis and performance evaluation.
• Effective communication and interpersonal abilities to drive innovation, work collaboratively with peer architecture, design teams, and senior management.
• Previous experience with high-speed memory technology pathfinding work with limited upfront guidance, pushing the boundaries of technology.
• A B.S., M.S., or Ph.D. in Computer Science, Computer Engineering, or Electrical Engineering (or equivalent experience).
• 18+ years of experience in SoC or memory system architecture preferably in complex SoC development, memory development companies, CPU/GPU and AI development.