Senior AI/ML ASIC Architect: AI Storage & xPU Accelerator

SanDisk; California; On-site; USD 180,000 - 320,000; Full time

Job summary

Sandisk is seeking an AI/ML ASIC Architect to develop architectures for AI Storage Solutions and accelerators. You will drive frontend architecture, collaborate across RTL/DV/FW and product planning, and push innovations for high-performance, power-conscious datacenter solutions.

You will work with cross-functional teams to define SoC requirements, assess PPA tradeoffs, and guide pre/post-silicon validation efforts while shaping the roadmap for next-generation AI storage accelerators.

Qualifications

• Bachelor's/Master's/PhD in Computer/Electrical Engineering with 15+ years of hands-on architecture experience.

Responsibilities

• Drive AI/ML ASIC architecture for AI Storage with accelerators over UCIe/PCIe/CXL.
• Author architecture specifications for AI/ML xPU-based accelerators.
• Define I/O subsystem and PCIe DMA architectures and interactions with subsystems.
• Create modular I/O subsystem architectures for Chiplet/monolithic/3D form factors.
• Scope SoC requirements with customers and cross-functional teams to meet PPA/schedule targets.
• Define DMA hardware/software/firmware interfaces with embedded subsystems and CPUs.
• Guide pre-silicon design/verification and post-silicon validation.
• Improve AI/ML ASIC performance via hardware/software co-optimization and roadmap influence.
• LLM workload analysis to identify performance opportunities in products.
• Experience architecting components like HBM, PCIe/UCIe/CXL, NoC, DMA, Firmware interactions, NAND, xPU.

Job description

Sandisk is seeking an AI/ML ASIC Architect to develop architectures for AI Storage Solutions and accelerators. You will drive frontend architecture, collaborate across RTL/DV/FW and product planning, and push innovations for high-performance, power-conscious datacenter solutions.

You will work with cross-functional teams to define SoC requirements, assess PPA tradeoffs, and guide pre/post-silicon validation efforts while shaping the roadmap for next-generation AI storage accelerators.