Geronimo Bergk Intelligent Sensing & Machine Learning
I want to develop intelligent systems that can perceive and understand physical signals and adapt to real-world conditions. I am interested in the intersection of sensing, signal processing, and machine learning, particularly in how intelligent systems can remain robust, efficient, and reliable outside controlled laboratory settings.
I am a PhD student in Computer Science at ETH Zürich, based at Empa and supervised by Prof. Christian Holz (SIPLAB). My research focuses on robust physiological monitoring from wearable sensors, combining multimodal sensing, signal processing, and machine learning with controlled experiments and field studies. I study how sensing quality, algorithms, and system constraints shape reliable inference of human physiological state, with the goal of building monitoring systems that remain reliable beyond the lab.
Before my PhD, I was Managing Consultant in Data Science & AI at Horváth, an international management consultancy, where I developed data-driven decision systems for large organizations. Previously, as a Research Associate at Fraunhofer HHI, I worked on machine learning, forecasting, telemetry, and control for communication systems under operational constraints. This work resulted in seven peer-reviewed publications and the Fraunhofer HHI Emerging Scientist Award for an outstanding master’s thesis.
Engineering principle
I am driven by a system-level perspective that fixes real deployment constraints early, investigates effects isolated in controlled experiments, and judges learning systems by robustness, efficiency, and operability.
Research interests
- Multimodal physiological sensing and signal analysis for robust inference of human state, health, and performance
- Machine learning and signal processing for multimodal, noisy, and time-varying sensor data
- Robustness, generalization, and experimental evaluation of intelligent sensing systems across users, conditions, and environments
- Hardware-aware machine learning and Edge AI for resource-constrained sensing platforms, considering computation, energy, latency, and on-device inference
Industry practice
- Design and deployment of data-driven decision systems under strict reliability, auditability, and governance constraints
- Large-scale forecasting and simulation systems operating under uncertainty, incomplete data, and real-time constraints
- Applied AI and machine learning systems with strong requirements on robustness, interpretability, and organizational accountability
Education
- Ph.D. in Computer Science, 2026 - present ETH Zürich
- M.Sc. in Electrical Engineering, 2021 Technische Universität Berlin
- B.Sc. in Electrical Engineering, 2017 Technische Universität Berlin