Summary
Daniel Lachner-piza is a Clinical Data Scientist with a PhD in Biomedical Engineering and eight years of experience applying machine learning to noisy physiological signals, particularly EEG. He builds end-to-end solutions—from C++ and embedded signal processing to Python-based ML pipelines and interactive annotation tools—that detect rare, low-amplitude biomarkers and make clinical datasets actionable. His work spans deep learning for biosignal segmentation, unsupervised and weakly-supervised methods, and production tooling using TensorFlow/PyTorch, MNE, and MLflow. He has industry and academic experience scaling pipelines over terabytes of EEG, containerizing databases, and delivering clinician-facing dashboards and software like the elpi annotation tool. Comfortable bridging hardware, firmware, and data science, he also brings hands-on experience optimizing parallel C++ code and firmware for medical devices. Now based in Calgary, he is pursuing industry roles in neurotech and digital health to translate physiological data into improved diagnostics and patient outcomes.
7 years of coding experience
15 years of employment as a software developer
PhD (Dr.-Ing.), Biomedical/Medical Engineering, PhD (Dr.-Ing.), Biomedical/Medical Engineering at Albert-Ludwigs-Universität Freiburg im Breisgau
Master of Science (M.Sc.), Biomedical/Medical Engineering, Master of Science (M.Sc.), Biomedical/Medical Engineering at Universität Bern
Spanish, English, German, French