I'm a senior research engineer at the Dynamical Inference Lab working on machine learning algorithms for representation learning and their application to neuroscience supervised by Steffen Schneider. Currently, I'm building core infrastructure for explainability research including 1) a framework for empirical identifiability and consistency, 2) software libraries & data engines around sparse autoencoder (SAE) training, and 3) software for annotating and hosting concepts extracted by SAEs. I'm also interested in training transformer and dynamics models on brain data at scale to study how multi-modal neural datasets can be compressed into foundation models.
I’m also lead engineer at KI macht Schule, a non-profit organization teaching machine learning basics to high school students. We provide teachers with modern teaching materials, AI tools, and infrastructure through our open teaching hub and offer student courses and teacher trainings on AI in Germany, Switzerland, and Austria. We have a great network of volunteers in nine cities who do science outreach directly in schools. If you want to help educate the next generation of students and make them literate in AI, consider joining our team!