About Me

I am a PhD student at the Max Planck Institute for Human Cognitive and Brain Sciences, where I focus on making AI tools more trustworthy. My journey into this field began with a master’s degree in electrical engineering, followed by experiences in both academia and industry. I briefly worked in Charley Wu’s HMC Lab in Tübingen and served as an AI Engineer at Appsfactory in Leipzig before joining Nico Scherf’s lab for my current research.

My work focuses on enhancing the reliability and trustworthiness of Deep Reinforcement Learning (RL) algorithms. To me, trustworthy AI means building intelligent systems that are less prone to failure, more transparent, and aligned with human objectives. I investigate methods to ensure RL algorithms adhere to safety constraints, avoid risky behavior, and remain robust against downstream changes or adversarial conditions. You can find a comprehensive review of trustworthy RL here.