AI/ML ASIC Architect

About the role

In this AI/ML ASIC Architecture position, you will develop AI Storage Solutions based on advanced system architectures and AI/ML Accelerator ASIC architecture specifications for Sandisk’s next generation products. You will drive, initiate, and analyze the frontend architecture of the AI/ML Accelerator product. As an AI/ML ASIC Architect, you will help drive new architecture initiatives that leverage state-of-the-art frontend interfaces like UCIe, PCIe, CXL, etc., integrating AI Storage Solutions with xPU in a 3D package system.

You will exercise your technical expertise and excellent communication skills to collaborate with design and product planning teams, delivering innovative and highly competitive adaptive accelerator solutions. Typical activities include writing architecture specifications, working with other architects, and collaborating with RTL/DV/Simulation/Emulation/FW teams to evaluate changes and assess performance, power, area, and endurance of the product. You will work closely with exceptional colleague engineers to innovate and develop products that will change the data-centric architecture paradigm.

Responsibilities

• Drive the AI/ML ASIC architecture that integrates AI Storage with GPU/TPU/xPU accelerators, with a focus on I/O subsystems connected over UCIe/PCIe/CXL.
• Author architecture specifications in clear and concise language for AI/ML xPU-based Accelerators using AI Storage Solutions.
• Define I/O subsystem and PCIe DMA architectures, including their interactions with internal embedded processor-subsystems, Network on Chip, Memory controllers, and FPGA fabric.
• Create flexible and modular I/O subsystem architectures deployable in Chiplet, monolithic, or 3D form factors.
• Work with customers and cross-functional teams to scope SoC requirements, analyze PPA (Power, Performance, Area) tradeoffs, and define architectural requirements that meet PPA and schedule targets.
• Define SoC subsystem and DMA hardware, software, and firmware interactions with embedded processing subsystems and SoC CPUs on the device side and Host CPUs.
• Guide and assist pre-silicon design/verification and post-silicon validation during the execution phase.
• Improve AI/ML ASIC Architecture performance through hardware & software co-optimization, post-silicon performance analysis, and influencing the strategic product roadmap.
• Perform LLM workload analysis and characterization of ASIC and competitive datacenter/AI solutions to identify opportunities for performance improvement.
• Architect one or more components of AI/ML accelerator ASICs such as HBM, PCIe/UCIe/CXL, NoC, DMA, Firmware Interactions, NAND, xPU, or fabrics.
• Drive the AI Storage Solutions frontend system architecture with GPU/TPU/NPU/xPU to match or exceed next-generation HBM bandwidth.
• Architect memory-efficient inference/training systems utilizing techniques like pruning, quantization with MX format, continuous batching/chunked prefill, and speculative decoding.
• Collaborate with internal and external stakeholders/ML researchers to disseminate results and iterate rapidly.

Requirements

• Bachelor’s degree in Computer/Electrical Engineering with 7+ years of experience, or Master’s degree with 5+ years of experience, or PhD with 3+ years of experience.
• 2+ years of experience authoring architecture specifications.
• Strong technical background architecting ASIC, SoC, or I/O subsystems involving PCIe/UCIe/CXL and DMA engines.
• Knowledge of I/O Subsystem and DMA interactions with internal embedded processor-subsystems (x86, RISC-V, or ARM) and external host CPU.
• Good understanding of computer/graphics architecture, ML, and LLM.
• Experience architecting GPU/TPU/xPU Accelerator systems with optimized high-bandwidth memory hierarchy and frontend architecture for multi-trillion parameter LLM training/inference, including Dense, Mixture of Experts (MoE) with multiple modalities (text, vision, speech).
• Expertise in KV cache optimization, Flash Attention, and Mixture of Experts.
• Deep experience optimizing large-scale ML systems and GPU architectures.
• Proficiency in principles and methods of microarchitecture, software, and hardware relevant to performance engineering.
• Knowledge of ARM Processors and AXI Interconnects.

Preferred Qualifications

• Familiarity with UCIe, CXL, NVLink, or UAL microarchitecture and protocols.
• Familiarity with high-speed networking: InfiniBand, RDMA, NVLink.
• Expert knowledge of transformer architectures, attention mechanisms, and model parallelism techniques.
• Multi-disciplinary experience, including familiarity with Firmware and ASIC design.
• Expertise in CUDA programming, GPU memory hierarchies, and hardware-specific optimizations.
• Proven track record architecting distributed training systems handling large-scale systems.
• Previous experience with NVMe storage systems, protocols, and NAND flash.

Pay

The salary range for this role is what we believe to be the range of possible compensation at the time of posting, applicable for jobs performed in California, Colorado, New York, or remote jobs that can be performed in these states. The final pay may vary based on factors including relevant education, qualifications, certifications, experience, skills, geographic location, shift, internal and external equity, and business needs.

You will be eligible to participate in Sandisk's Short-Term Incentive (STI) Plan, which provides incentive awards based on Company and individual performance. Depending on your role and performance, you may also be eligible for our annual Long-Term Incentive (LTI) program, consisting of restricted stock units (RSUs) or cash equivalents. RSU awards are also available to eligible new hires, subject to Sandisk's Standard Terms and Conditions for Restricted Stock Unit Awards.

Benefits

• Paid vacation time and sick leave.
• Medical, dental, and vision insurance.
• Life, accident, and disability insurance.
• Tax-advantaged flexible spending and health savings accounts.
• Employee assistance program.
• Voluntary benefit programs such as supplemental life and AD&D, legal plan, pet insurance, critical illness, accident, and hospital indemnity.
• Tuition reimbursement.
• Transit benefits.
• Applause Program.
• Employee stock purchase plan.
• Sandisk's Savings 401(k) Plan.