Microsoft's vision for Azure Machine Learning (ML) centers around democratizing ML and ensuring its accessibility to all enterprises, developers, and data scientists. We are seeking individuals to join our team entrusted with the responsibility of serving all internal and external ML workloads. With our current efforts, we are already catering to billions of requests daily, encompassing the most cutting-edge scenarios and models throughout the company

As a member of the Inference team, you will contribute to the development of the next generation of model serving. This includes hosting OpenAI models such as ChatGPT, as well as scaling model hosting for Bing and Office, tackling numerous captivating challenges at the intersection of AI and Cloud. We are actively seeking a highly skilled Software Engineer who possesses a profound passion for designing and constructing exceptionally reliable and available platforms, capable of supporting model inferencing on a massive scale

In addition to platform development, you will be tasked with addressing high throughput/low latency scenarios and spearheading performance optimization capabilities. This position provides a unique opportunity to thrive in an environment that fosters innovation, fosters collaborative teamwork, and upholds the pursuit of excellence, all in alignment with Microsoft's mission.