CareerPlan

Principal AI Silicon Architect

United States, California, Mountain ViewFull-time2026-10-15 → 2026-11-10

Core

Define end-to-end power architecture for high-power AI accelerator SoCs, managing tradeoffs across silicon, package, board, and system levels to maximize performance per watt.

Role type

Principal AI Silicon Architect (Power Architecture)

Builds

High-power AI accelerator SoCs and associated power delivery systems

Domain

Semiconductor / AI Hardware / Power Architecture

Deliverable

production ML models

Required skills

SoC power architecture, power delivery (PDN), power management (DVFS, gating), thermal management, workload analysis, multi-die/chiplet design, system-level tradeoffs

Preferred skills

Experience with AI accelerators, GPUs, HPC processors, server CPUs, voltage/frequency scaling, energy-efficiency optimization

Technologies

AI accelerators, GPUs, HPC processors, server CPUs, multi-die architectures, chiplet architectures

Responsibilities

Define SoC and package-level power-management architecture; manage workload power excursions and peak/sustained power constraints; partner with performance teams to maximize performance per watt; drive architectural tradeoffs across performance, power, thermal, and cost; translate requirements into power budgets and design targets; define SoC-to-system interfaces for power and thermal management; provide technical leadership from architecture through silicon bring-up and optimization.

Seniority

Principal, hands-on IC with strategic influence