Research Internships at Microsoft provide a dynamic environment for research careers with a network of world-class research labs led by globally-recognized scientists and engineers, who pursue innovation in a range of scientific and technical disciplines to help solve complex challenges in diverse fields, including computing, healthcare, economics, and the environment.

We are seeing massive growth in artificial intelligence (AI) scenarios and increasing hardware diversity across cloud and edge. Today, inference is a major challenge. The shift in trend towards deep learning models has exponentially increased the computation costs. In addition, the continuous evolving landscape, in models and hardware diversity, contributes to the complexity and difficulty of efficient inferencing.

Within our Systems Innovation research group, we approach this from a unified perspective of model compression/optimization, hardware-aware inference engines, and fleet optimization. We closely collaborate with multiple research teams and product groups across the globe. Some of the research problems we are currently working on include: leverage transfer learning to efficiently share capacity across multiple scenarios; design hybrid models that span cloud and edge; or, designing microarchitecture for novel silicon.

We are looking for Research Interns to help advance the state of the art of efficient AI. The ideal candidate will have background in deep learning, model compression, and/or hardware, and the motivation and ambition to apply this in a real-world setting.