Soc Compute/memory Subsystem Architect

Intel Intel · Semiconductors · Leixlip, Ireland

Intel is seeking a Senior SoC Compute & Memory Architect to define and drive the architecture of compute complexes and high-performance memory subsystems for next-generation IPU/DPU platforms. This role involves end-to-end architecture of CPU clusters, cache hierarchies, coherency models, and memory subsystems, optimizing for performance, scalability, power efficiency, and programmability in hyperscale environments. Responsibilities include cache hierarchy and coherency, memory subsystem, IO memory and virtualization, system-level integration, power efficiency, and defining a multi-generation architecture roadmap. The role requires collaboration with various teams and strong leadership skills.

What you'd actually do

  1. Define and evolve multi-level cache hierarchy (private/shared caches, system-level cache).
  2. Architect system memory subsystems including: -DDR / LPDDR interfaces. -Memory controllers and scheduling policies. -Bandwidth provisioning and scaling strategies.
  3. Define architecture for SMMU/IOMMU supporting virtualization-heavy IPU workloads.
  4. Architect integration between: -Compute subsystem. -Network subsystem (packet processing pipelines). -Storage and accelerator subsystems.
  5. Define compute and memory strategies for power efficiency and DVFS scalability.

Skills

Required

  • SoC / CPU / memory subsystem architecture
  • CPU architecture and cache hierarchies
  • Memory subsystems (DDR/HBM, controllers, QoS)
  • Coherent/Non-Coherent interconnect architectures
  • system-level performance and PPA tradeoff analysis
  • Drive architecture definition from concept to silicon
  • Batchelor's degree in Electrical Engineering, Computer Engineering, or in a STEM related Field of Study

Nice to have

  • Post Graduate degree in Electrical Engineering, Computer Engineering, or in a STEM related Field of Study
  • ARM and x86 compute and memory subsystem experience, including NUMA systems, cache coherency, or large scale platform architectures
  • Experience with IPU / SmartNIC or accelerator centric SoCs, particularly in cloud and hyperscale environments
  • Familiarity with PCIe, CXL, and memory semantics for high performance IO
  • Track record of multi generation architectural ownership and mentoring other architects

What the JD emphasized

  • end-to-end architecture
  • SoC / CPU / memory subsystem architecture
  • CPU architecture and cache hierarchies
  • Memory subsystems (DDR/HBM, controllers, QoS)
  • Coherent/Non-Coherent interconnect architectures
  • system-level performance and PPA tradeoff analysis
  • Drive architecture definition from concept to silicon
  • multi-generation architectural ownership