**Overview**

M365 Copilot Inference is a high-impact engineering team advancing applied AI and large-scale machine learning across Microsoft. The team designs and operates the platform powering Microsoft 365 Copilot experiences, running at massive GPU (Graphics Processing Unit) scale across multiple regions and SKUs in global datacenters. It builds core LLM (large language model) API (Application Programming Interface), routing, and capacity control plane services to deliver low-latency, highly available Copilot experiences.

We’re hiring a Principal Software Engineering Manager to lead a team focused on control plane automations for capacity buildout. This is a hands-on technical leadership role centered on how Copilot capacity is requested, planned, deployed, and operated.

The manager will contribute to capacity planning and custom model deployment automation, partnering closely with peer managers and adjacent areas to shape how the broader control plane evo...