Independent Researcher
Jan 2026 – present
Machine learning & mechanistic interpretability
Pre-registered and ran a study of cross-layer dynamics in transformer factual recall across six language models from three families, entirely on consumer hardware. All code will be made public once the paper is published. Also ran a grokking (delayed generalization) study on EMG gesture-recognition networks.
Paper: link TBA
Grokking study
Software Engineer
Jan 2024 – Jan 2026
openDAQ by Dewesoft and Hottinger Brüel & Kjær
Helped shape the open source data acquisition SDK that enables cross-platform, multi-language, and DAQ hardware vendor interoperability. Implemented core C++ features, documentation, CI/CD, release, testing, Python bindings, and metrics dashboards (Grafana/InfluxDB on AWS).
github.com/openDAQ/openDAQ
Young Researcher, Teaching Assistant
Oct 2018 – Oct 2022
University of Maribor, Faculty of Electrical Engineering and Computer Science, System Software Laboratory
Led research in electromyography (EMG) and teaching. Built end-to-end EMG pipelines (MATLAB, R), ML models for biosignals (Python, TensorFlow, Keras), and taught computer vision (OpenCV). Supervised students and contributed to peer-reviewed work.
Most cited paper: On the reuse of motor unit filters in high density surface electromyograms recorded at different contraction levels
Bibliography: COBISS researcher profile