Senior AI Interconnect Architect for Large-Scale XPUs

Credo Semiconductor, Inc.; San Jose (CA); On-site; USD 220,000 - 280,000; Full time

Job summary

Credo Semiconductor, Inc. in San Jose, CA, seeks a Principal AI System Architect to solve system interconnect challenges linking XPUs into scalable AI infrastructure.

You will define memory/interconnect topology across node, rack, and cluster to enable efficient large‑scale LLM training and inference, with hands‑on NPU hardware experience preferred. Reporting to AVP, XPU system AI interface, you will lead architecture decisions, mentor a team of architects, and collaborate with silicon, memory,

Qualifications

• Bachelor's degree in Computer Engineering, Electrical Engineering, Computer Science, or related field required.
• Ten years in XPU or AI interconnect system design, architecture and micro architecture working experience.
• Five cycles of complete ASIC tapeouts.
• Strong foundational understanding of computer architecture, including GPU, NPU, and/or CPU design principles; deep, hands‑on NPU hardware architecture expertise.
• Familiarity with large language model architectures and distributed training/inference concepts.
• Demonstrated analytical ability with track record of independent study and synthesis of technical material.
• Strong cross‑functional leadership and communication skills with compiler, software, SOC & backend teams.

Responsibilities

• Define the memory and interconnection architecture linking XPUs to memory and across node boundaries.
• Solve communication and topology bottlenecks during distributed LLM training and inference.
• Define how XPUs utilize memory and interconnect fabric for workloads.
• Work with silicon, memory, networking, and software teams to specify interconnect fabric requirements.
• Bring hands‑on NPU hardware architecture judgment to interconnect and system design decisions.
• Track leading open LLM architectures to anticipate stress on interconnect and topology.
• Lead and mentor a team of architects focused on system interconnection.

Skills

XPU interconnect design

ASIC tapeouts

GPU/NPU/CPU design principles

distributed training/inference

leadership & mentoring

cross-functional collaboration

system architecture

Education

Bachelor's degree in Computer Engineering / Electrical Engineering / Computer Science

Tools

PCIe

Ethernet

RDMA

Job description

Credo Semiconductor, Inc. in San Jose, CA, seeks a Principal AI System Architect to solve system interconnect challenges linking XPUs into scalable AI infrastructure.

You will define memory/interconnect topology across node, rack, and cluster to enable efficient large‑scale LLM training and inference, with hands‑on NPU hardware experience preferred. Reporting to AVP, XPU system AI interface, you will lead architecture decisions, mentor a team of architects, and collaborate with silicon, memory,