We are looking for a dedicated master’s student to join us in the Connected Intelligence Unit at RISE.

The Connected Intelligence Unit is part of RISE Computer Science in Kista. The current research focus is on devising intelligent autonomous systems for controlling and allocating resources in future computer and communication networks. Among the group's key technologies are the Internet of Things (IoT) and Edge computing. The unit conducts projects together with industry and academic partners from Sweden and across the world.

Background and Purpose
Large Language Models (LLMs) are increasingly used in software engineering to generate code, implement features, and support developers throughout the software lifecycle. However, their effectiveness may depend strongly on the structure and quality of the existing codebase. Code created with extensive AI assistance may also develop different structural characteristics than human-written code, potentially affecting future AI-assisted development.

This raises an important question for the long-term use of AI in software engineering: Does continuous use of AI-assisted development make subsequent AI-assisted development more costly or difficult?

Thesis Description
This thesis aims to investigate how the structure and development history of a software project affect the ability of LLMs to implement new features. You will select suitable open-source projects and recreate them using AI-based development tools, simulating projects built with extensive AI assistance.

New features with clearly defined completion criteria will then be implemented using AI on both the original and AI-generated codebases. The process will be evaluated based on development time, token consumption, number of attempts, and successful completion. The results will help identify whether AI-generated code structures influence the efficiency of future AI-assisted software development.

Terms:
Start Time: As soon as possible
Scope: 30 hp
Location: RISE Computer Science, Kista, Stockholm. Option to partially work remotely.

Who are you?
We expect you to have a solid knowledge of machine learning theory, good programming skills (especially Python), and an interest in computer systems and solving complex problems. You are also currently enrolled in a masters programme.

We are looking forward to receiving your application!
To know more, please contact the supervisor Mariano Scazzariello (mariano.scazzariello@ri.se). The thesis will be conducted together with the KTH Networked System Laboratory and KTH Machine-Intelligence for Networks and Distributed Systems Laboratory. Applications should include a brief personal letter, CV, recent grades, and a code excerpt. Candidates are encouraged to send in their application as soon as possible but at the latest by the 15th of October 2026. Suitable applicants will be interviewed as soon as applications are received.