Summary
Maximillian Vording is a Senior Data Scientist based in Copenhagen with a decade of experience bridging Bayesian deep learning, active and semi-supervised methods, and experimental design for biological and nanoscale sensing applications. He focuses on making ML more data-efficient and interpretable by integrating human- and sensor-in-the-loop workflows, probabilistic generative models, and optimal acquisition strategies to "know what we don't know." His background spans a DTU PhD project on nano-mechanical biosensors, applied work in learning analytics and conversational AI at Laerdal, and translational research in single-cell variational autoencoders and clinical time-series. Maximillian blends rigorous statistical modelling with practical deployment, aiming to reduce friction in data collection and to visualize uncertainty for better experimental decisions. An under-the-radar strength is his cross-disciplinary fluency—physics, cognitive science, and machine learning—which he leverages to tackle complex experimental systems where both sensors and humans are active agents.
10 years of coding experience
Bachelor's degree Fysik, Bachelor's degree Fysik at Københavns Universitet - University of Copenhagen
Technical University of Denmark