Microsoft's Azure Machine Learning (ML) team is seeking a Principal Software Engineer to join their Inference team, which builds the model-serving platform for large models including OpenAI generative models. The role involves working on a platform that serves billions of requests per day for cutting-edge ML scenarios. The position focuses on designing and building a highly reliable, available platform to support model inferencing at scale, particularly for Bing and Office applications.
As a Principal Engineer, you'll be working at the intersection of AI and Cloud, tackling challenges related to high throughput and low latency scenarios. The role requires extensive experience in software development, with a focus on performance optimization and system reliability. You'll be part of a team that's democratizing ML technology, making it accessible to enterprises, developers, and data scientists worldwide.
The position offers comprehensive benefits including industry-leading healthcare, educational resources, and parental leave. Microsoft provides a collaborative environment with opportunities for professional growth and impact at scale. The hybrid work arrangement allows up to 50% work from home, providing flexibility while maintaining team collaboration.
This role is perfect for someone who is passionate about AI infrastructure, has deep technical expertise, and wants to contribute to building the future of machine learning platforms. You'll be working with cutting-edge technology while solving complex problems that impact millions of users globally.