Microsoft's AI Frameworks team is seeking a Software Engineer II to join their innovative team developing AI software that enables running AI models across various platforms, from supercomputers to mobile devices. The role focuses on optimizing inference performance for OpenAI and other Large Language Models (LLMs) that serve trillions of inferences daily across major Microsoft products.
The position offers an opportunity to work at multiple levels of the AI software stack, including fundamental abstractions, programming models, compilers, and runtimes. You'll be responsible for benchmarking and optimizing LLM performance on various hardware platforms, helping achieve Microsoft Azure's capex goals through efficient model deployment.
This hands-on technical role requires strong software design and development skills, with a focus on solving complex problems in building end-to-end AI systems. The team operates at the intersection of AI algorithmic innovation, purpose-built AI hardware, systems, and software, collaborating directly with OpenAI and other partners.
The ideal candidate will have experience with high-performance computing, GPU optimization, and machine learning frameworks. You'll join a collaborative and inclusive culture that values growth mindset and innovation, working on projects that directly impact major Microsoft products including Office, Windows, Bing, and SQL Server.
Benefits include industry-leading healthcare, educational resources, parental leave, and generous time away. Microsoft offers a supportive environment for professional growth, with opportunities to network and contribute to cutting-edge AI technology development.