Staff Design Engineer, Edge Ai, Google Cloud

Google Google · Big Tech · Tel Aviv, Israel +1

This role focuses on designing custom silicon solutions for Edge AI products within Google Cloud, specifically for distributed inference technology. The engineer will lead ASIC subsystem development, define hardware/software interfaces, and ensure high-performance, low-latency, and reliable deployment of complex AI models on edge hardware.

What you'd actually do

  1. Lead a complex ASIC subsystem.
  2. Understand how it interacts with software and other ASIC subsystems to implement groundbreaking data center.
  3. Define high-performance hardware/software interfaces.
  4. Write micro architecture and design specifications.
  5. Define efficient micro-architecture and block partitioning/interfaces and flows.

Skills

Required

  • RTL development for ASIC subsystems using Verilog
  • speed interfaces such as PCIe, InfiniBand
  • low latency, security, and reliability principles
  • micro architecture
  • design
  • verification
  • logic synthesis
  • timing closure

Nice to have

  • scripting languages (e.g., Python or Perl)
  • arithmetic units
  • bus architectures
  • processor design
  • accelerators
  • memory hierarchies
  • high performance and low power design techniques
  • FPGA
  • emulation platforms
  • SoC architecture
  • assertion-based formal verification

What the JD emphasized

  • Edge-AI product
  • distributed inference technology
  • latency and reliability are mission-critical
  • robust, autonomous solutions
  • localized processing
  • deploy complex AI models
  • sophisticated hardware platforms
  • intelligence is embedded exactly where the action happens

Other signals

  • Edge AI
  • distributed inference
  • custom silicon solutions
  • high-performance intelligence
  • localized processing
  • deploy complex AI models