New 
Principal Performance Architect
 Microsoft | |
 United States, California, Mountain View | |
 Jul 25, 2025 | |
|
OverviewMicrosoft's MAIA architecture team is looking for outstanding SoC Performance Architects to develop SoC models and analyze performance of Microsoft's custom AI accelerators. Microsoft Silicon, Cloud Hardware, and Infrastructure Engineering (SCHIE) is the team behind Microsoft's expanding Cloud Infrastructure and responsible for powering Microsoft's "Intelligent Cloud" mission. SCHIE delivers the core infrastructure and foundational technologies for Microsoft's over 200 online businesses including Bing, MSN, Office 365, Xbox Live, Teams, OneDrive, and the Microsoft Azure platform globally with our server and data center infrastructure, security and compliance, operations, globalization, and manageability solutions. Our focus is on smart growth, high efficiency, and delivering a trusted experience to customers and partners worldwide and we are looking for passionate engineers to help achieve that mission. As Microsoft's cloud business continues to grow the ability to deploy new offerings and hardware infrastructure on time, in high volume with high quality and lowest cost is of paramount importance. To achieve this goal, the MAIA Architecture team is instrumental in defining and delivering operational measures of success for hardware manufacturing, improving the planning process, quality, delivery, scale and sustainability related to Microsoft cloud hardware. We are looking for seasoned engineers with a dedicated passion for customer focused solutions, insight and industry knowledge to envision and implement future technical solutions that will manage and optimize the Cloud infrastructure. We are looking for a Principal Performance Architect to join the team.
ResponsibilitiesDevelop and test SoC and IP models, including model integration Analyze performance and bottlenecks for critical deep learning workloads Actively collaborate with architects, and provide critical feedback for future SoC Prototype opportunities for performance and power optimizations, and trade-offs on AI accelerators | |