Rack-Scale AI Hardware Architect

What you'll do

• Lead rack and platform architecture across boards, chassis, interconnect, cooling, power delivery, and serviceability.
• Develop and model scale-up and scale-out fabrics, translating LLM partitioning and traffic needs into performance, power, thermal, and cost requirements.
• Validate the reference design in hardware and guide it toward deployment with partners and customers.

What they ask for

• Bachelor’s degree in Electrical Engineering, Mechanical Engineering, Computer Engineering, or a related field, with relevant experience in server, datacenter, HPC, or AI system design.
• Demonstrated ownership of dense rack-based server systems taken to production, including specifications for ODM and OEM partners.
• Expert command of copper and optical interconnect technologies and signal-integrity trade-offs.
• Expert command of rack cooling architecture and ability to reason across interconnect, power, thermal, mechanical, and software boundaries, supported by modeling and trade studies.

Nice to have

• Master’s degree or PhD in a related field.
• Hyperscale or OCP experience, including ORv3, or experience with small-accelerator systems, LLMs at scale, advanced packaging, or production reference designs.

Tools

PCIe, high-speed Ethernet, SerDes, DAC, twinax, AOCs, ORv3, CDUs

AI focus

Architect rack-scale AI compute systems and jointly model LLM partitioning, inter-layer traffic, and collectives to determine fabric, memory, and topology requirements.