I'm an RF, electromagnetics, and electronics engineer with a multidisciplinary background spanning high-frequency electromagnetic simulation, mm-wave systems, analog CMOS design, and applied machine learning. My work focuses on combining physics-based engineering methods with computational and AI/ML approaches to solve complex problems efficiently and accurately.
My industrial R&D experience at NXP Semiconductors, through the EU-funded INNOSTAR consortium project focused on 5G and 6G connectivity, involved developing an AI/ML-assisted workflow to predict far-field radiation patterns from near-field IC data. The project covered the full engineering lifecycle, including problem definition, simulation methodology, dataset generation, deep-learning model development, verification and validation, and technical reporting within an international research consortium.
My technical foundation spans the main professional EM simulation environments — ANSYS HFSS, Keysight ADS, and CST Studio Suite — used across FEM and Method of Moments solvers. I've developed deep-learning architectures (CNN, U-Net) in PyTorch and built the data preprocessing pipelines that make them trainable from simulation outputs. Before that, I spent two years on integrated photonics research, designing dispersion-engineered waveguides published in international journals.
I'm currently based in Eindhoven, with technical interests spanning RF and electromagnetics, mm-wave systems, EMC, electronics and semiconductor technologies, EM simulation, and AI/ML for engineering applications.
