Overview

‍

‍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.

AI System Architecture group within Azure is looking to hire a Research Intern with an understanding of AI accelerator architectures (e.g. Graphics Processing Unit (GPUs)), and proficiency in programming generative AI algorithms onto novel AI Hardware (HW). The candidate's responsibilities spans across the stack - from optimizing the model serving engine, mapping models across HW devices and implementing optimal tiling/kernel-fusion strategies within the device. The candidate will also be responsible for benchmarking resultant performance on hardware to ensure efficient end-to-end model inference.

‍

‍

‍Responsibilities‍

Research Interns put inquiry and theory into practice. Alongside fellow doctoral candidates and some of the world’s best researchers, Research Interns learn, collaborate, and network for life. Research Interns not only advance their own careers, but they also contribute to exciting research and development strides. During the 12-week internship, Research Interns are paired with mentors and expected to collaborate with other Research Interns and researchers, present findings, and contribute to the vibrant life of the community. Research internships are available in all areas of research, and are offered year-round, though they typically begin in the summer.

‍

‍

‍Qualifications‍

Required Qualifications

• Currently enrolled in a Ph.D. program in Computer Science, Electrical Engineering or a related STEM field
• 1+ years of experience working in Graphics Processing Unit (GPU)/AI Accelerator programming

‍

Other Requirements

• Research Interns are expected to be physically located in their manager’s Microsoft worksite location for the duration of their internship.
• In addition to the qualifications below, you’ll need to submit a minimum of two reference letters for this position as well as a cover letter and any relevant work or research samples. After you submit your application, a request for letters may be sent to your list of references on your behalf. Note that reference letters cannot be requested until after you have submitted your application, and furthermore, that they might not be automatically requested for all candidates. You may wish to alert your letter writers in advance, so they will be ready to submit your letter.

‍

Preferred Qualifications

• Experience working with model serving stacks such as SGLang/vLLM.
• Ability to identify bottlenecks with workloads - through analytical modeling and actual hardware benchmarking.
• Familiarity of compute graphs of Generative AI models including LLMs and image/video diffusion models.
• Understanding of common techniques used for workload optimization such as model sharding, operator fusion, tiling etc.
• Proficiency in programming AI accelerators - Coding in Triton or C to achieve desired goals.
• High levels of motivation and agency.

‍