Collaborative Intelligence Internship (Applying Large Language Models to Spreadsheets) Cambridge 2024
Spreadsheets are the world’s most widely-used programming technology and the definitive low-code and no-code platform. The recent success of large language models (LLMs) creates an opportunity to take a qualitative step forward, to extend dramatically the reach of what end users can do with spreadsheets.
We are hiring multiple interns to join an ambitious, multidisciplinary research team on the future of work, and spreadsheets or computational notebooks in particular. We are a global team with members across Microsoft including Calc Intelligence (MSR Cambridge), RiSE (MSR Redmond), Excel and PROSE.
The interns will join us for summer 2024 in Cambridge UK for a 4-month internship starting in May. The exact internship projects will be chosen to fit the expertise of successful applicants. We are interested in a broad range of areas related to our co-audit research, including:
- Improving the experience of authoring and debugging code for end-user programmers
- Improving the experience of reading and understanding spreadsheets
- Using insights from type systems, static analysis, program synthesis and machine learning to generate, debug and repair computations produced by LLMs
- Improving the conversational capabilities of code-generating chatbots
We seek interns with expertise in one or more of the following research areas: programming-languages, HCI and user experience, machine learning. There is a genuine possibility that your work could have real-world impact. Past interns have been heavily involved in impactful projects that have transitioned into products. Our team’s impact on many millions of customers features in the history of research collaborations with Microsoft Excel, the Microsoft Wall of Fame, and even XKCD 2453.
For interns of all disciplines
- Work in a multi-disciplinary team
- Generate novel and original academic research insights
- Write and present your findings in technical documents or research papers
For interns in an HCI/design discipline
- Conduct mixed methods user research (e.g., surveys, controlled experiments, ethnography, interviews etc.)
- Translate findings into practical design insights
- Deploy prototype technologies and evaluate their impact on user practice
For interns in a programming languages/machine learning discipline
- Invent technical solutions to enable new and better user experiences
- Develop and iterate on prototypes in collaboration with our research and engineering teams, building on our existing platforms
- Apply benchmarks and appropriate evaluation metrics to demonstrate improvements in technical solutions.
- Must be enrolled in a PhD in one or more of the following research areas: human-computer interaction, end-user programming, human-factors in programming languages, programming languages and compilers, including program synthesis, or artificial intelligence applied to code or knowledge. For applicants with a design background, we will consider outstanding Masters-level students with research experience as evidenced by publications in peer-reviewed conferences or journals.
- Experience or interest in working in the spreadsheet domain.
- Experience in doing LLM research.
- Experience of software prototyping at various levels of fidelity, from sketches and wireframes to interactive prototypes preferred.
- Good spoken and written English.
- One or two papers at top HCI, EUP, PL, ML conferences or journals is preferred, but not essential. A writing sample of unpublished work should be included if a publication is not available.