AI Hardware System Architect
$250k - $350k • San Jose, California, United States
Posted 8d ago
Job Location
San Jose, California, United States
Tech Stack
Remote Work Policy
On-site
Categories
AI Engineer
About the job
SambaNova is seeking a Senior RDU System Architect to join their team. This role is crucial in transforming silicon into shippable AI infrastructure, specifically focusing on SambaRack-class server and rack designs, the interconnect fabric linking RDUs, and the power and cooling systems required for dense AI compute. You will define the architecture from board to cluster level, make critical build, buy, and co-design decisions with hardware partners, and author the specifications they will build to. The position involves guiding the platform from initial architecture definition through bring-up, qualification, and fleet deployment, ensuring alignment with product and customer priorities.
Responsibilities
- Define the architecture of RDU-based server and rack platforms, from board layout and chassis design to full-rack integration.
- Translate product and customer requirements into system specifications for engineering teams and vendors.
- Select and validate major system components, balancing performance, power, and manufacturability.
- Build performance and cost models to compare rack configurations.
- Architect the scale-up and scale-out interconnect fabric for training and inference clusters.
- Define the power delivery architecture and cooling strategy for dense AI compute racks.
- Collaborate with signal and power integrity engineers to validate designs.
- Evaluate ODM/OEM and component vendor proposals against system requirements.
- Identify and mitigate schedule or technical risks in partner designs.
- Maintain an understanding of the vendor and technology landscape for platform roadmapping.
- Define bring-up, validation, and qualification plans, including RAS and telemetry targets.
- Lead root-cause investigations for platform behavior discrepancies.
- Partner with software, ML performance, and datacenter operations teams to optimize system architecture for workloads.
- Brief executive leadership on architecture tradeoffs and roadmap alignment.
- Mentor engineers on system architecture methodology and improve team processes.
Requirements
- B.S. or M.S. in Electrical Engineering, Computer Engineering, Computer Science, or equivalent practical experience.
- 12+ years architecting hardware systems for hyperscale, HPC, or AI/ML infrastructure.
- Deep, hands-on background in at least one systems domain (interconnect, power delivery, thermal/cooling, or mechanical) for large-scale AI accelerator, HPC, or hyperscale systems.