INTERNSHIP DETAILS

Research Intern - Multi-Agent Systems

CompanyMicrosoft
LocationCambridge
Work ModeOn Site
PostedJanuary 16, 2026
Internship Information
Core Responsibilities
The intern will design, train, and fine-tune modern LLM architectures using Pytorch on GPU clusters. They will also work on multi-agent design and system-level optimizations.
Internship Type
full time
Company Size
226614
Visa Sponsorship
No
Language
English
Working Hours
40 hours
Apply Now →

You'll be redirected to
the company's application page

About The Company
Every company has a mission. What's ours? To empower every person and every organization to achieve more. We believe technology can and should be a force for good and that meaningful innovation contributes to a brighter world in the future and today. Our culture doesn’t just encourage curiosity; it embraces it. Each day we make progress together by showing up as our authentic selves. We show up with a learn-it-all mentality. We show up cheering on others, knowing their success doesn't diminish our own. We show up every day open to learning our own biases, changing our behavior, and inviting in differences. Because impact matters. Microsoft operates in 190 countries and is made up of approximately 228,000 passionate employees worldwide.
About the Role
Overview

Multi-agent AI systems are driving the growth of intelligence scaling and real-world impact. At Microsoft Research Cambridge, future AI infrastructure (FAI) team is looking for two passionate research interns to explore future multi-agent AI systems together. This research internship is about ML and systems co-design. To build better multi-agent AI, we will explore what new capabilities are needed for future agent models, such as recursive LLMs, latent memory, and task planning. At the same time, we will look into innovative system designs like better agent-level parallelism, agent communication intensity, and distributed memory systems. With FAI team’s AI hardware innovations (see AOC and MOSAIC), the outcome of this work will lead to strong impact on future AI systems design through the collaboration with other MSR research teams and Microsoft product teams.  



Responsibilities

 

  • Work on designing, training, fine-tuning modern LLM architectures using Pytorch and other relevant tools on GPU clusters. 

  • Work on post-training open-source models into agentic and/or recursive variants with emerging capabilities such as planning, state-tracking, and improved latent memory, potentially by using gradient-free methods such as evolution strategies 

  • Work on multi-agent design and implementation, integrating system-level optimizations (e.g. shared latent KV-cache, agent-level parallelism) using relevant framework tools and inference backends like vLLM and SGLang. 



Qualifications

Required/Minimum Qualifications:   

  • Being enrolled in a PhD program of computer science, artificial intelligence, machine learning, computer engineering, electrical and electronics engineering, or other related fields. 

Other Requirements:  

  • Experience working on research projects related to ML and systems design. 

  • Experience in model post training, reinforcement learning / evolution strategies, or supervised fine tuning. 

  • Experience in building high-performance LLM inference systems using SGLang or vLLM. 

Preferred/Additional Qualifications: 

  • Publications in top ML conferences and/or systems conferences 


This position will be open for a minimum of 5 days, with applications accepted on an ongoing basis until the position is filled.



Microsoft is an equal opportunity employer. All qualified applicants will receive consideration for employment without regard to age, ancestry, citizenship, color, family or medical care leave, gender identity or expression, genetic information, immigration status, marital status, medical condition, national origin, physical or mental disability, political affiliation, protected veteran or military status, race, ethnicity, religion, sex (including pregnancy), sexual orientation, or any other characteristic protected by applicable local laws, regulations and ordinances. If you need assistance with religious accommodations and/or a reasonable accommodation due to a disability during the application process, read more about requesting accommodations.

Key Skills
Machine LearningSystems DesignPytorchGPU ClustersModel Post TrainingReinforcement LearningEvolution StrategiesSupervised Fine TuningHigh-Performance LLM InferenceSGLangvLLMMulti-Agent DesignTask PlanningState-TrackingLatent MemoryAgent Communication
Categories
TechnologyScience & ResearchEngineeringData & AnalyticsSoftware
Research Intern - Multi-Agent Systems - InternshipsHQ