Sebastian Krauss
I completed my Bachelor's in Mechatronics in Stuttgart, where I gained hands-on experience through multiple internships at Bosch, including a three-month assignment in China. During my Master's in Autonomous Engineering in Karlsruhe, I broadened my international perspective with an Erasmus semester in France and worked as a student researcher at Fraunhofer. My growing interest in AI led me to focus my master's thesis on sensor-based map generation for autonomous driving using CGAN models at Bosch. In 2024, I joined Validaitor, a start-up in Karlsruhe that specializes in testing and evaluating AI models for fairness, safety, and trustworthiness, as an AI Engineer.
Session
Fairness and safety are fundamental criteria for building trustworthy and high-quality AI systems, whether they are credit scoring models, hiring assistants, or healthcare chatbots. But what does it truly mean for an AI system to be fair and safe? In this talk, I will explore the potential risks and challenges associated with these principles and introduce various approaches and techniques for evaluating AI systems. The discussion will center on applications powered by Large Language Models (LLMs).