Welcome!

I am an Assistant Professor in computer science at CMU, where I build intelligent tools for software engineering.

Research

The goal of my work is to make safe, effective programming more accessible through intelligent software assistance tools. AI-based tools hold great promise for extracting expertise from public data about software (on GitHub, StackOverflow, etc.) and presenting this in a timely fashion to help new and inexperienced developers.

My research work towards this goal across three frontiers: 1. investigating new applications of AI in SE to understand the community’s needs broadly and provide practical value (e.g., FSE’18, FSE’21 IRV, EMSE’21); 2. analyzing current models and trends to make sure our results are impactful (ICSE’19, FSE’21, CACM’22); 3. building new models based on these insights (ICLR’20, NeurIPS’21, ICLR’22), including PolyCoder, briefly the largest open-source model trained exclusively on source code (get it here!).

Collaborations with Industry

SE research is most impactful when we maintain a connection to software development companies. That is not to say that all our papers must have practical application, but rather that our broader research agenda should be at least partially informed by an understanding of computer programming in practice. I maintain these ties through frequent collaboration with industrial partners, including part-time employment (I was a visiting faculty at Google), research grants & collaborations (incl. with IBM, Google), and various other visits (incl. past internships at Microsoft). My door is always open for new industry collaborations! Contact me if interested.

Google Brain: As a visiting researcher (until August 2021), I studied characteristics and modeling implications of how developers write code from big data. Currently collaborating on another project.

IBM: Studying the relation of code and natural language in several practical setting in this (grant-based) collaboration.

Microsoft Research: Worked with several researchers on topics including type inference and invariant detection, from a machine learning perspective.

Contact

Affiliation: Institute of Software Research, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA

Email & General Info: See my ISR faculty page

GitHub, Twitter, Scholar