Konstantin Kirchheim
When should a machine-learning system no longer be trusted?
I study the evaluation and monitoring of machine-learning systems under distribution shift. My research combines out-of-distribution detection, structured reasoning, and reproducible evaluation to identify situations in which learned models may behave unreliably.
I am a PhD researcher in computer science at Otto von Guericke University Magdeburg and was previously a visiting graduate student at the University of Waterloo. My broader objective is to understand how model-level evidence can support defensible claims about the reliability and deployment of machine learning in safety-critical systems.
