Our Inference team is responsible for building and maintaining the tools and systems that enable Microsoft AI researchers to run models easily and efficiently. Our work empowers researchers to run models in RL, synthetic data generation, evals, and more. We are joint stewards of one of the largest compute fleets in the world. The team is responsible for optimizing compute efficiency on our heterogeneous data centers as well as enabling cutting-edge research and production deployment. We are an applied research team that is embedded directly in Microsoft AI’s research org to work as closely as possible with researchers. We are vertically integrated, owning everything from kernels to architecture co-design to distributed systems to profiling and testing tools.

Work alongside researchers and engineers to implement frontier AI research ideas.

Introduce new systems, tools, and techniques to improve model inference performance.

Build tools to help debug performance bottlenecks, numeric instabilities, and distributed systems issues.

Build tools and establish processes to enhance the team’s collective productivity.

Find ways to overcome roadblocks and deliver your work to users quickly and iteratively.

Enjoy working in a fast-paced, design-driven product development cycle.

Embody our Culture and Values.