Master Thesis: Interaction-Derived Knowledge Bases for Self-Improving UI Agents(m/w/x)

Beschreibung

In this role, you will focus on enabling UI Agents to learn from past interactions by designing a continuously updated knowledge base. Daily activities will involve researching existing methods, developing innovative solutions, and collaborating with a team to validate ideas.

Anforderungen

• •Currently pursuing a Master’s degree in Computer Science or related field
• •Excellent programming skills in Python
• •Proven hands-on experience with Large Language Models (LLMs) and popular LLM frameworks and tooling
• •Profound experience designing or working with agentic AI systems
• •Ability to work independently, think analytically, and structure complex problems
• •Very good English skills (written and spoken)
• •Based in Germany
• •Prior experience with Retrieval-Augmented Generation (RAG) or other memory-augmented LLM architectures
• •Experience with experimental evaluation or applied research in AI / ML
• •First experience with writing or publishing scientific papers
• •German language skills are helpful, but not required

Aufgaben

• •Conduct a comprehensive literature review
• •Explore and design novel approaches
• •Develop and implement prototypes
• •Define and conduct experiments
• •Present your work in team presentations
• •Collaborate closely with researchers and engineers

Tools & Technologien

Benefits