Description

You'll own compute hardware from architecture through bring-up, designing boards that deliver ≥10 TFLOPS for onboard AI/ML inference and science data processing. You pick components, design boards, and debug with the software team, owning everything from schematic capture to board-level validation.

Requirements

• Experience in board-level design and validation of high-performance compute hardware
• Proficiency in power delivery network design for multi-rail systems exceeding 500W
• Expertise in integrating GPU/CPU compute modules with high-speed interconnects
• Ability to define thermal interface requirements for power dissipation and temperature limits

Responsibilities

• Design compute boards delivering ≥10 TFLOPS for onboard AI/ML inference and science data processing
• Architect and implement power delivery networks for high-complexity carrier boards with 500W+ multi-rail designs
• Integrate GPU or CPU compute modules onto custom PCBs with high-speed coherent interconnects
• Define thermal interface requirements including power dissipation budgets and junction temperature limits
• Own hardware from schematic capture through board-level validation and bring-up with software team