Master Thesis - Development of Trustworthy Agentic AI (f/m/div)

#WeAreIn to create tiny chips and big careers.

The future won’t wait... why should you? Join us and make a difference. Whether you join as a student, intern, or trainee, you'll be part of something real - real projects, real impact, and real opportunities to grow.

Are you in?

Your role

Key responsibilities in your new role

• Experience research: You conduct a comprehensive literature review on Agentic AI, AI safety, trustworthiness frameworks, uncertainty quantification, AI governance, and autonomous agent architectures
• Holistic overview: You analyze current architectural vulnerabilities, security risks, and limitations of existing trustworthiness mechanisms in operational AI agent systems
• Shape the future: You develop and evaluate trustworthiness approaches for a baseline domain-specific AI agent and assess their effectiveness in mitigating hallucinations and unsafe behavior
• Be Creative: You prototype novel trustworthiness mechanisms such as uncertainty-aware reasoning, semantic traceability, neuro-symbolic guardrails, runtime validation, and zero-trust execution logging
• Take responsibility: You define and evaluate quantitative metrics including hallucination detection accuracy, auditability, compliance verification, uncertainty calibration, and system performance overhead
• Keep your colleagues informed: You present research findings, recommendations, and future directions to AI and technology teams
• Stay up to date: You monitor emerging developments in Trustworthy AI, AI Safety, Agentic AI, and AI Governance to incorporate state-of-the-art approaches into your work

Your profile

Qualifications and skills to help you succeed

• Study Field: You are currently in the final stage of your Master's studies in Computer Science, Artificial Intelligence, Data Science, Software Engineering, Electrical Engineering, or a related field
• Interests: You have a strong interest in Generative AI, Large Language Models (LLMs), AI Agents, Trustworthy AI, AI Safety, or AI Governance
• (Work) experience: You have practical experience with Python and modern AI/ML frameworks such as PyTorch, TensorFlow, LangChain, LangGraph, or similar technologies
• Work Style: You enjoy analytical thinking, conducting independent research, and translating theoretical concepts into practical implementations
• Personality: You bring curiosity, initiative, and a structured approach to solving complex technical challenges in a research-driven environment
• Skills: You ideally have knowledge of uncertainty quantification, explainable AI, AI compliance, knowledge graphs, agent architectures, or software security
• Language Skills: You are fluent in English; German language skills are considered a plus

Please attach the following documents to your application:

• CV in English
• Certificate of enrollment at university
• Excerpt of the study regulations for the thesis
• Latest grades transcript (not older than 6 months)
• High school report

Further links:

• Find out what we are looking for in your CV
• Find out how the student application process works with us
• Discover our student website