Research Intern - Frontier Tuning
Job in
Redmond, King County, Washington, 98073, USA
Listing for:
Microsoft Corporation
Apprenticeship/Internship
position
Listed on 2026-11-21
Job specializations:
-
Research/Development
Job Description & How to Apply Below
* 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.
The Frontier Tuning research team in Microsoft 365 is seeking Research Interns for summer 2027 in Redmond, WA, the San Francisco Bay Area, CA, or Baltimore, MD.
Our mission is to help every organization own its intelligence:
Artificial Intelligence (AI) that knows, reasons, and works the way the organization does. We capture how an enterprise works, including its knowledge, sense making, workflows, tools, and expert judgment, in reinforcement learning environments (RLEs). These environments serve as a gym in which AI agents improve by tuning their skills, evaluations, harnesses, and underlying models, while customer data stays within the customer's trust boundary.
Our research is the foundation of Frontier Tuning, announced at Microsoft Build 2026 and available to makers and developers in Microsoft Copilot Studio, Microsoft Foundry, and Git Hub Copilot.
Enterprise work is a demanding testbed for AI. Tasks are long-horizon and open-ended, quality is judged against expert rubrics rather than a single correct answer, knowledge is spread across documents, conversations, slides, and drawings, and every organization works differently. We have shown that reinforcement fine-tuning in well-constructed enterprise environments lets smaller tuned models outperform the latest frontier models on such tasks, at lower cost.
We work side by side with customers, product teams, and partners so that new methods reach real users quickly, and the gaps we find in the field shape our next research questions.
We are seeking Research Interns to advance the science of adapting AI agents to the enterprise. Research Internship projects will focus on topics such as:
+ Reinforcement learning and post-training for agents, including RL for open-ended tasks without verifiable rewards, goal-driven training for long-horizon trajectories, tool use within training trajectories, harness-aware training, and efficient RL training and inference.
+ Enterprise environments and synthetic organizations, including scalable construction of realistic RL environments, simulation of multi-person collaboration, virtualized tools for side-effect-free training, and automatic generation of tasks, skills, and rubrics from enterprise signals.
+ Evaluation and rewards, including rubric-based grading, reliability of Large Language Models (LLM) judges, measuring environment quality, and evaluations that predict real-world value.
+ Learning from experts and from use, including learning from subject-matter-expert feedback, combining signals across the experts in a team, learning from sparse signals, and continual improvement after deployment.
+ Skills and organizational knowledge, including discovering (search), composing, and tuning agent skills, reasoning over organization-scale data, retrieval and embeddings, and deciding when knowledge belongs in context, in skills, or in model weights.
+ Multimodal tuning, including adapting models to slides, documents, and technical drawings, and to an organization's style and voice.
This role is ideal for PhD students who want research that is both novel and grounded in real needs, and who want to see their ideas move into products used by organizations worldwide. You will collaborate with researchers, applied scientists, engineers, and product managers, and we encourage interns to publish their work.
** 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.
** Additional Responsibilities*
* + Design, implement, and evaluate new methods in our training,…
To View & Apply for jobs on this site that accept applications from your location or country, tap the button below to make a Search.
(If this job is in fact in your jurisdiction, then you may be using a Proxy or VPN to access this site, and to progress further, you should change your connectivity to another mobile device or PC).
View / Apply for Jobs
Matching My Jurisdiction
(If this job is in fact in your jurisdiction, then you may be using a Proxy or VPN to access this site, and to progress further, you should change your connectivity to another mobile device or PC).
View / Apply for Jobs
Matching My Jurisdiction