Senior AI System Architect for Memory & Compute

Sandisk; Milpitas (CA); On-site; USD 170,000 - 260,000; Full time

Job summary

Sandisk is seeking a System Architect to drive system-level solutions for advanced memory technologies and AI inference infrastructure in Milpitas, CA. You will optimize compute-memory bottlenecks, latency, and power while mapping workloads to hardware across chiplet, SoC, and software co-design.

The role demands deep memory technology expertise, proficiency in C/C++, Python, RTL, and strong collaboration to guide design teams and deliver scalable, high-performance solutions.

Qualifications

• Master's or Ph.D. in Electrical Engineering, Computer Engineering, or Computer Science.
• 10+ years in System Architecture, SoC design, and memory system development.
• Knowledge of DRAM, DDR, LPDDR, GDDR, NAND technologies.
• Experience with AI accelerators, GPUs, Neural Processing Engines.
• Proficiency in C/C++, Python, RTL design, and system-level modeling.
• Familiarity with PCIe, CXL, NoCs, Ethernet, RDMA interconnects.

Responsibilities

• Define system-level architecture co-optimized with software.
• Develop performance and power models for optimization.
• Map AI/ML workloads to hardware requirements.
• Collaborate across software and hardware teams for memory subsystems and interconnects.
• Explore advanced memory concepts like in-memory/near-memory computing and novel packaging.
• Provide technical leadership and documentation for design teams.

Skills

Memory technologies

C/C++

Python

RTL design

System-level modeling

AI accelerators

Interconnects (PCIe, CXL, NoCs)

Communication & mentorship

Education

Master's or PhD in Electrical/Computer Engineering or CS

Job description

Sandisk is seeking a System Architect to drive system-level solutions for advanced memory technologies and AI inference infrastructure in Milpitas, CA. You will optimize compute-memory bottlenecks, latency, and power while mapping workloads to hardware across chiplet, SoC, and software co-design.

The role demands deep memory technology expertise, proficiency in C/C++, Python, RTL, and strong collaboration to guide design teams and deliver scalable, high-performance solutions.