Principal Software Engineer - GPU Performance

Microsoft's AI Platform organization is seeking a Principal Software Engineer to join their team working on GPU performance analysis and optimization. This role is part of the team building Azure OpenAI, Azure Machine Learning, Cognitive Services, and global Azure AI infrastructure. The position involves working with state-of-the-art AI models and Microsoft's next-generation supercomputers, including the Maia-100 AI accelerator.

The role requires deep expertise in GPU optimization, with a focus on developing and optimizing software for large-scale AI training and inference workloads. You'll be working directly with OpenAI on models hosted on the Azure OpenAI service, collaborating with hardware teams and partners to build software stacks for advanced AI systems.

As a Principal Engineer, you'll be responsible for developing fundamental abstractions, programming models, runtimes, libraries, and APIs. The position demands strong technical skills in C/C++, Python, and GPU development languages like CUDA, along with experience in performance analysis and optimization of large language models.

The compensation is competitive, ranging from $161,600 to $286,200 per year (higher in SF and NYC areas), with comprehensive benefits including healthcare, educational resources, and parental leave. Microsoft offers a collaborative environment where innovation is encouraged, and diversity is actively sought to drive better solutions for customers.

This is an opportunity to work at the cutting edge of AI technology, contributing to Microsoft's mission of empowering every person and organization on the planet to achieve more. The role combines technical depth with broad impact, requiring both hands-on development skills and the ability to collaborate across multiple disciplines.