Job Title:

Principal AI Memory Systems ArchitectLocation:

San Jose, CA or Irvine, CACompensation:

$250K - $300K base plus equity

Requirements:

AI Systems Architecture, Memory Hierarchy, CXL, HBM, AI Inference, Computer Architecture, Memory Disaggregation, Processing-in-Memory (PIM), GPU / Accelerator Architecture, ASIC/SoC ArchitectureCompany BriefWe are a leading provider of high-performance modular memory subsystems and next-generation storage-class memory solutions. We specialize in cutting-edge technologies that enable innovation in AI, cloud computing, and enterprise infrastructure. Our product portfolio includes

DDR4/DDR5

DIMMs, NAND-based SSDs, and advanced interconnect technologies such as CXL and PCIe.

RoleThis is a senior architecture role for someone who understands how AI workloads translate into memory, bandwidth, latency, compute, interconnect, power, and system-level requirements. The role partners closely with the Chief AI Systems Architect, AI Product Strategist, AI Software Architect, and R D teams to develop next-generation AI hardware and memory architectures.

We are particularly interested in investigating opportunities involving:

AI memory hierarchy evolution for larger models and context windowsHBM, DDR, CXL, storage, and memory-tiering strategiesNear-memory and processing-in-memory architecturesReducing data movement, power consumption, and system costExpanding effective memory capacity and utilizationNew hardware architectures that outperform current AI systemsKey ResponsibilitiesArchitect AI systems, memory subsystems, and accelerator platformsTranslate AI workload requirements into memory, compute, bandwidth, and latency specificationsDesign solutions leveraging HBM, DDR, CXL, memory pooling, disaggregation, caching, and persistent memoryAnalyze architectural tradeoffs across performance, power, capacity, area, and costCharacterize AI workloads including LLM inference, RAG, agentic AI, long-context inference, and KV-cache managementEvaluate emerging technologies such as CXL memory expansion, memory compression, and near-memory computingPartner with software teams to optimize runtime, memory management, scheduling, and workload orchestrationBuild architectural models, simulations, benchmarks, and proof-of-concept prototypesDefine product architectures, technical roadmaps, and system specificationsConduct technical due diligence on startups, technologies, IP, and M&A opportunitiesRequired QualificationsBS/MS in Electrical Engineering, Computer Engineering, Computer Science, or related field (PhD preferred)10+ years in computer architecture, memory systems, semiconductor design, AI hardware, or related fieldsDeep expertise in memory hierarchy and computer architectureExperience with HBM, DDR, CXL, PCIe, UCIe, high-speed interconnects, and/or AI acceleratorsStrong understanding of AI/ML workloads and architectural tradeoffsDemonstrated experience developing complex semiconductor or computing systemsProven ability to translate system requirements into hardware architectures and specificationsPreferred ExperienceLLM inference and transformer architecturesKV-cache systems and AI inference runtimes (e.g., vLLM)CUDA/GPU architecturesCXL 2.x/3.x, memory pooling, and memory disaggregationProcessing-in-memory and near-memory computingAI networking and storage-class memoryASIC/SoC architecture, RTL, and microarchitectureHardware/software co-design and architectural modelingEdge AI systems#EnghpBenefitsVacation/PTOMedicalDentalVisionEquity401k w/ match