Doctoral student in computer science focused on AI-assisted development (PA2024/1728)

The position offers a unique setup in the Software Engineering Research Group (SERG), benefiting from the co-supervision of the Software Development and Environments Research Group (SDE). SERG is renowned for its impactful and methodical empirical research focused on large-scale software engineering. Concurrently, SDE specializes in pioneering technical research, innovative tools, languages, and methods designed to enhance software development practice. Both SERG and SDE belong to the Dept. of Computer Science, a vibrant international setting for education and research. Beyond software engineering, distinguished topics include artificial intelligence, computer graphics, and theoretical computer science.
More information about the Department of Computer Science - cs.lth.se 

The project utilizes an action research approach, embedding the doctoral student within the R&D activities at CodeScene, headquartered in Malmö. CodeScene develops a software engineering intelligence platform that identifies and prioritizes technical debt in extensive codebases.
More information about Codescene - codescene.com 

Developers often spend a significant amount of their time understanding and maintaining existing code. Although high-quality code can enhance productivity, reduce defect counts and vulnerabilities, and increase developer satisfaction, organizations frequently prioritize new feature implementation over code improvement. This leads to accumulating technical debt. The project posits substantial potential in applying Large Language Models (LLMs) to improve the maintainability of existing code through AI-driven refactoring.

CodeScene has recently introduced an AI refactoring feature that enables automated (LLM-based) improvement of code issues directly within the Integrated Development Environment (IDE). The deployment of this feature to real users provides an opportunity to gather large-scale quantitative feedback, forming the primary basis for the doctoral research.

Despite the promise of LLMs, they present inherent risks. Research indicates that the prompt-based, non-deterministic generation of code by LLMs can introduce security vulnerabilities and alter functional behavior unexpectedly. Consequently, trust is central to AI refactoring. The project will explore this concept from two angles. Firstly, by designing safeguards to enhance the trustworthiness of AI refactoring, such as techniques to reject low-confidence code changes. Secondly, by developing a user interface that fosters user trust in the refactoring process. Utilizing CodeScene’s detailed telemetry, these aspects will be examined through A/B testing.

The project is part of the Software track of the Wallenberg AI, Autonomous Systems, and Software Program (WASP), and the PhD student will be enrolled in the WASP graduate school offering advanced courses and extensive networking opportunities.
More information about WASP graduate school - wasp-sweden.org/graduate-school/

The PhD student will participate in the WASP research school, which includes doctoral courses, summer schools, winter conferences, and international study trips.

The main duties of doctoral students are to devote themselves to their research studies, which includes participating in research projects and third-cycle courses. The work duties will also include teaching and other departmental duties (of no more than 20%).

Description of the work duties:

• Research within the subject area
• Teaching in the second and third cycles
• Collaboration with industry (beyond CodeScene) and wider society

A person meets the general admission requirements for third-cycle courses and study programmes if the applicant: 

• has been awarded a second-cycle qualification, or
• has satisfied the requirements for courses comprising at least 240 credits of which at least 60 credits were awarded in the second cycle, or
• has acquired substantially equivalent knowledge in some other way in Sweden or abroad.

A person meets the specific admission requirements for third-cycle studies in Computer Science if the applicant has: 

• at least 60 second-cycle credits at an advanced level (M.Sc. level courses) that are relevant to this topic, or
• M.Sc. degree in Computer Science, Electrical Engineering, Information and Communication Technology, Engineering Physics, or Engineering Mathematics.

Additional requirements

• Very good oral and written proficiency in English
• Strong programming skills
• Strong interest in programming languages and program analysis
• Good knowledge of mathematics
• Interest in machine learning, especially LLMs

Selection for third-cycle studies is based on the student’s potential to profit from such studies. The assessment of potential is made primarily on the basis of academic results from the first and second cycle. Special attention is paid to the following:

Other assessment criteria:

• Experience with compiler construction and static program analysis
• Experience with Clojure
• Work experience as a software developer

Consideration will also be given to good collaborative skills, drive, and independence, and how the applicant, through experience and skills, is deemed to have the abilities necessary for successfully completing the third cycle programme.

Lund University is a public authority which means that employees get particular benefits, generous annual leave and an advantageous occupational pension scheme. Read more on the University website about being a Lund University employee Work at Lund University . 

Only those admitted to third-cycle studies may be appointed to a doctoral studentship. Third-cycle studies at LTH consist of full-time studies for 4 years. A doctoral studentship is a fixed-term employment of a maximum of 5 years (including 20% departmental duties). Doctoral studentships are regulated in the Higher Education Ordinance (1993:100), chapter 5, 1-7 §§.

Applications shall be written in English and include a cover letter stating the reasons why you are interested in the position and in what way the research project corresponds to your interests and educational background. The application must also contain a CV, degree certificate or equivalent, and other documents you wish to be considered (grade transcripts, contact information for your references, letters of recommendation, etc.). You are also asked to answer the selection questions. Applications will be reviewed on a rolling basis, and all submissions will be considered.

Welcome to apply!