Research Intern - Memory & Orchestration in Large Language Models

Microsoft Corporation•Redmond, WA

28d

About The Position

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. Microsoft Research is seeking Research Interns to join us in pushing the boundaries of Artificial Intelligence (AI) capabilities with large language models (LLMs) and multimodal models. Our mission is to create new LLM memory representation and orchestration systems in the pursuit of innovative and disruptive offerings for both enterprise and consumer contexts. We are particularly interested in developing new methods for leveraging and training various types of LLM memory representations. This includes structures such as knowledge graphs, graph and text embeddings, and the creation of advanced retrieval augmented generation (RAG) systems. We also look towards understanding research that allows us to measure the temporal changes to these structures over time as we pursue better quality retrieval and the ability to generate temporal explanations.

Requirements

Currently enrolled in a PhD program in Computer Science, Machine Learning, Artificial Intelligence, or a related STEM field.
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.

Nice To Haves

Experience with Python ecosystem
Experience with LLMs and prompt engineering
Experience with agentic systems and workflows

Responsibilities

Conducting hands-on research into systems for memory and orchestration of LLMs and multimodal models.
Investigating new embedding techniques, including graph embeddings and methods that measure changes over time.
Developing advanced retrieval augmented generation systems to enhance LLM capabilities.
Collaborating with interdisciplinary teams of researchers and engineers on challenging and impactful projects.
Presenting research findings and participating in research discussions.

Stand Out From the Crowd

Upload your resume and get instant feedback on how well it matches this job.

Upload and Match Resume