This list contains only the countries for which job offers have been published in the selected language (e.g., in the French version, only job offers written in French are displayed, and in the English version, only those in English).
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. In M365 Research, we are dedicated to pioneering advancements in Artificial Intelligence (AI) and Systems, driving the transfer of innovative technologies into our products, establishing Microsoft’s leadership in technical domains and enhancing community engagement. We closely collaborate with multiple research teams and product groups across the globe who bring a multitude of technical expertise in machine learning, cloud systems and software engineering. We communicate our research both internally and externally through peer-reviewed scientific publications, open-source releases, blog posts, patents, and industry conferences. For this position, you should have a strong software engineering background with experience in AI/ML for code intelligence. Our research focuses on advancing coding agents that can understand real-world codebases and autonomously execute software engineering tasks end-to-end. Topics of interest include building LLM-based coding agents for repository-scale feature implementation and bug fixing, enhancing agents’ ability to plan and use developer tools effectively (e.g., tests, linters, CI workflows), and improving reliability through iterative feedback from code reviews and test results
Job Responsibility
Conduct research on coding agents and agentic systems under the guidance of a mentor, aligned with ongoing projects
Collaborate with researchers and engineers to design and develop intelligent agent pipelines for software engineering tasks (e.g., code generation, debugging, and automation)
Apply machine learning and program analysis techniques to real-world problems in software engineering and AI agents
Design, implement, and evaluate agent-based systems, including LLM-based pipelines, tool-use agents, and multi-step reasoning workflows
Develop prototypes or systems that integrate language models with external tools, APIs, or code execution environments
Run experiments, analyze model/system performance, and iterate based on empirical results
Present research progress and technical findings, and contribute to technical reports, documentation, or publications
Requirements
Currently pursuing a PhD in Computer Science, Artificial Intelligence, Machine Learning, or a related field
Must have at least one additional semester or quarter remaining after completion of the internship
Experience in machine learning, natural language processing, or Agent systems
Strong programming skills in Python or similar languages
Nice to have
Experience with LLM-based coding systems or agentic tools for software development (e.g., repository understanding, code modification, test generation)
Ability to collaborate effectively in cross-functional, multi-disciplinary teams across research and product groups
Research contributions demonstrated through publications in top venues such as NeurIPS, ICML, ICLR, ACL, EMNLP, ICSE, FSE or related conferences