Engineering Manager, ML Performance

About the role

Google Core ML org Engineering Manager for the TPU Performance team, optimizing custom AI chips via low-level kernel programming (CUDA/Triton/Pallas) and compiler optimization (MLIR/OpenXLA) - deep ML systems/hardware specialization, not general dev tooling/platform engineering.

Requirements

• Experience in ML accelerators and low-level kernel programming
• Experience with compiler optimization and framework integration
• Technical leadership managing engineers across multiple teams

What you'll do

• Manage TPU Performance team maximizing speed/efficiency of Google's custom AI chips
• Guide optimization for internal AI models and external AI companies
• Oversee deployment of large-scale ML infrastructure projects

Where this was posted

• LinkedIn

  last seen 2mo ago
  View on LinkedIn