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.
Advances in Artificial Intelligence (AI) increasingly depend on breakthroughs in systems and architecture, where hardware, models, and software must be co-designed to scale efficiently. This Research Internship offers the opportunity to explore next-generation AI systems through performance modeling, architectural analysis, and emerging inference mechanisms. Research Interns will investigate topics such as disaggregated inference, memory-architecture, and interconnect technologies specifically focused on request scheduling and key-value (KV) caching optimizations. This role is ideal for students passionate about understanding AI systems end-to-end and shaping the architectural foundations of tomorrow’s intelligent datacenters.
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
- Investigate and evaluate emerging disaggregated KV cache architectures.
- Implement a hierarchical storage architecture with multiple tiers
- GPU Memory: Active working set of KV caches currently used by the model
- CPU DRAM: Hot cache for recently used KV chunks using pinned memory for efficient GPU-CPU transfers
- Local Storage: Large-scale local caching (NVMe, local disk)
- Build Peer-to-Peer (P2P) service KV cache sharing architecture that enables direct, high-performance cache transfer between multiple LLM serving instances without requiring centralized cache servers.
Qualifications
Required Qualifications
- Currently enrolled in a PhD program in Computer Science, Electrical/Computer Engineering, or a related field.
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
- Research experience in areas such as computer architecture, AI/ML systems, performance modeling, distributed systems, or hardware–software co-design.
- Programming skills in Python, C/C++ with experience building prototypes, simulators, or performance analysis tools.
- Familiarity with modern AI workloads and/or deep learning frameworks (e.g., PyTorch).
- Demonstrated ability to define and pursue original research directions in AI systems or architecture.
- Ability to collaborate effectively with researchers across disciplines and work in cross-group, cross-cultural environments.
- Proficient communication and presentation skills for sharing complex technical insights.
- Ability to think creatively and approach system and architecture challenges with unconventional or innovative solutions.
- Experience with PyTorch, CUDA, Triton, or performance-simulation tools.
- Background in large-scale system design, AI inference bottleneck analysis, or modeling cost/performance tradeoffs. Understanding of accelerator, memory-system, or interconnect design principles.
