Summary
Hossein Ghorbanfekr is a computational scientist with 10 years of experience applying high-performance computing and machine learning to molecular simulation and materials discovery. Currently at imec, he develops ML-driven molecular dynamics workflows for biomolecular systems aimed at accelerating drug discovery. His background spans HPC platform engineering and data science at VITO—where he deployed GPU clusters, trained domain-specific LLMs, and built real-time ML pipelines for imaging and waste sorting—through to academic work on neural network potentials for 2D materials during a PhD and postdoc at the University of Antwerp. He combines low-level performance tuning (C/C++/Fortran optimizations, MPI) with modern ML stacks (PyTorch, TensorFlow) and hands-on cluster ops (SLURM, Kubernetes). Notably, he contributes open-source tools for MD workflows and neural network potential development, bridging reproducible research and production-ready HPC. Based in Antwerp, he brings a rare mix of computational physics rigor and production ML/HPC engineering to interdisciplinary research problems.
10 years of coding experience
1 year of employment as a software developer
Doctor of Philosophy - PhD Physics, Doctor of Philosophy - PhD Physics at University of Antwerp
Bachelor of Science Physics, Bachelor of Science Physics at University of Guilan
Master of Science Physics, Master of Science Physics at Sharif University of Technology
persian (farsi), English, Dutch