MSc Thesis: Evaluating Agentic AI-Driven Test Automation

Are you excited about AI and software development? Want to explore how AI agents can transform software testing and help improve the quality of medical software? Then this thesis project could be for you.

Project Description

RaySearch develops a software system called RayStation, used by over a thousand clinics worldwide for radiation treatment planning for cancer. In software development in general, and in medical device software in particular, testing is an important part of the development process to ensure quality of the product. Testing can be performed at several levels, for example unit testing, integration testing and user interface testing and can be either automated or manual. Good coverage of automated tests is desirable, both to reduce time-consuming manual work and to be able to find bugs earlier in the development process.

This project aims to develop and evaluate a framework that uses AI agents to automate manual UI tests. The project will assess the framework’s reliability, coverage, and potential to improve the efficiency and traceability of product testing. The framework could also be extended to other products.

You will have the opportunity to explore the most recent AI agents in this work using Microsoft Visual Studio Code and GitHub Copilot, connected to RayStation. You will develop and evaluate different skills for the AI agents as part of the project.

To be eligible for this position, you are a master's student within computer engineering, engineering physics, or a related field, and have excelled in your studies. You have an interest in software development, AI, testing and contributing to our mission. Experience with github copilot and working with skills and agents is an advantage.

Application

Please apply to the position through the link below. Selection and interviews will be ongoing. We do not accept applications by e-mail.

Application Link.