Praktika / Abschlussarbeiten

Are you passionate about Generative AI, educational technologies, and improving the learning experience of students? We are offering an exciting Master’s thesis opportunity to design and implement an AI mentor for our writing feedback platform Peer.
Peer is a educational tool that supports students in improving their writing through structured AI-generated feedback. We now want to take Peer to the next level:
Your mission will be to develop an AI-based assistant that acts as a smart writing mentor. This assistant will guide students through the feedback they receive on their writing, help them understand what to revise and why, answer follow-up questions students might have, and engage in voice- or text-based interactions depending on student preference. The assistant should be both context-aware and educationally supportive, using large language models and/or speech interfaces to foster deeper engagement and learning.

We are looking for Master’s students with:
•    Strong interest in AI, NLP, HCI, or Educational Technology
•    Experience with Python and/or web development
•    Familiarity with LLM APIs (e.g., OpenAI, Anthropic, etc.)
•    Experience with dialogue systems or speech interfaces is a plus

If you are interested, please send a short email with your CV to enkelejda.kasneci(at)tum.de.
 

Key words: Webcam-based eye-tracking, benchmarking, comparative study

Eye-tracking allows to collect data of eye movements, which can be used to analyse cognitive processes such as reading difficulties. However, most high-quality eye-tracking technologies rely on dedicated hardware, limiting their accessibility and scalability. This is particularly challenging in educational technologies, where eye-tracking-based tools for learning and especially reading assessment should ideally function on standard consumer devices such as laptops or tablets, without sacrificing accuracy. In these areas, it is essential to obtain high-quality data using webcam-based eye-tracking systems. 

For more information contact Franziska Kaltenberger (franziska.kaltenberger[at]tum.de) and Enkeleda Thaqi (enkeleda.thaqi[at]tum.de)

VR provides immersive and interactive learning environments for supporting skill development among learners. Moreover, VR can also serve as a valuable tool for enhancing the pedagogical strategies of teachers. In this project, our main objective is to develop an intelligent VR learning platform specifically designed for training teachers in data literacy skills. The platform will incorporate interactive features, including gamification elements and a Chatbot supported by Generative AI, to create engaging and effective learning experiences. 

Virtual Reality (VR) technology has revolutionized the way we learn and interact with information. In this project, we aim to design a VR classroom that leverages the power of generative behavior and text models to enhance the learning experience for students. The project is presumably suitable for students from computer science: games engineering, but also for all other students who have an interest in developing VR applications that integrate artificial intelligence.

For more information contact ozdelsuleyman(at)tum.de.