PhD Position Automated Code Refactoring of Software Engineering; FUSE lab

Want to rethink the future of software engineering at scale? Join researchers from TU Delft and Meta Platforms as a PhD student in the newly established FUSE Lab! Job description

As generative artificial intelligence is transforming the daily work of software engineers, TU Delft and the Meta Dev Infra team join forces in a research lab to investigate how we can leverage AI to advance the daily experience and productivity of software engineers at the scale of Meta's tens of thousands of software engineers.

Across several tracks, we will develop tools that rethink the future of software engineering. Our work will be informed by sound theories and supported by empirical data. In this project, we will use AI as an opportunity and address the challenges that emerge due to AI. Our goal is to conduct rigorous research, apply our results in practice at Meta and to educate the students of TU Delft about the new insights we gather.

We will focus on open science, sharing our results to help developers across the world.

Automated Code Refactoring

The focus is on exploring and evaluating the potential of LLM-based automated refactoring of codebases with the ultimate goal of reducing software complexity and improving code quality. We will investigate how LLMs can support and automate tasks such as enhancing maintainability and performance while also reducing technical debt and facilitating bug detection and bug fixing. The main modules include (1) capturing practitioners' experiences and expectations to establish a roadmap, (2) developing models and benchmarks for LLM-based refactoring, (3) designing autonomous agents, and (4) conducting studies to analyse real-world impact.

We are committed to creating a diverse and inclusive research environment and encourage applications from all qualified candidates, regardless of their background or experience. We believe that diversity contributes to a more innovative and creative research community.

If you do not meet some of the optional requirements listed, we encourage you to still apply and explain how your unique experience and skills can contribute to our research.

Required (by the Graduate School of TU Delft):

• Master's degree in Computer Science, Software Engineering, Artificial Intelligence, or a related field.
• Proficiency in the English language (https://(Use the "Apply for this Job" box below).)

Additional requirements:

• Research focus, characterized by curiosity, data fluency, and critical thinking
• Engineering mindset, including ability to create experimental prototypes and demonstrators
• Team player, good listener, and ready to help.

Delft University of Technology is built on strong foundations. As creators of the world-famous Dutch waterworks and pioneers in biotech, TU Delft is a top international university combining science, engineering and design. It delivers world class results in education, research and innovation to address challenges in the areas of energy, climate, mobility, health and digital society. For generations, our engineers have proven to be entrepreneurial problem-solvers, both in business and in a social context.

At TU Delft we embrace diversity as one of our core values and we actively engage to be a university where you feel at home and can flourish. We value different perspectives and qualities. We believe this makes our work more innovative, the TU Delft community more vibrant and the world more just. Together, we imagine, invent and create solutions using technology to have a positive impact on a global scale.

That is why we invite you to apply. Your application will receive fair consideration.

Challenge. Change. Impact!

The Faculty of Electrical Engineering, Mathematics and Computer Science (EEMCS) brings together three scientific disciplines. Combined, they reinforce each other and are the driving force behind the technology we all use in our daily lives. Technology such as the electricity grid, which our faculty is helping to make completely sustainable and future-proof. At the same time, we are developing the…