Overview
Lead hardware systems architecture for frontier AI compute, owning system-level design from package boundaries through racks and datacenter interfaces.
What you'll do
- Own system path-finding and architecture for your compute domain from concept to deployment.
- Write and own high-level requirements and specifications for systems, boards, interfaces, and racks.
- Drive interconnect and networking architecture across fabrics, NICs/switches, optics, and topology.
- Define validation, bring-up, and qualification strategy, including telemetry and reliability targets.
- Develop performance simulations and hardware “what-if” scenarios to evaluate architecture options.
- Partner with ML performance, infrastructure software, and datacenter teams to align hardware decisions with workloads.
What you'll need
- Deep, hands-on expertise in at least one core hardware-systems domain (e.g., interconnect, power, thermal) for large-scale compute or networking systems.
- Experience owning hardware system architecture at scale (machine, rack, row, and cluster) and authoring specifications/requirements.
- Experience taking hardware from architecture through bring-up to high-volume production deployment.
- Experience working with external hardware vendors and partners to review designs against specifications.
- Ability to reason about trade-offs across adjacent hardware domains (e.g., interconnect ↔ power ↔ thermal ↔ mechanical).
- Track record of technical leadership owning directional decisions and driving alignment.
- Strong written communication for specs and reviews used by many teams.
Details
- Location-based hybrid policy: expected in one of the offices at least 25% of the time.
Read the full description and apply on the company’s own careers page.
