Pantelis Vlachas
Research Affiliate
Zurich, Zurich, Switzerland
Summary
👤
Senior🎓
Top SchoolPantelis Vlachas is a machine learning research scientist and research affiliate at ETH Zürich with eight years of experience developing data-driven models for high-dimensional, nonlinear dynamical systems. He holds a PhD from ETH Zürich and builds practical, physics-aware ML frameworks—such as LED and MSM-LSTM—that achieve large simulation speedups while preserving physical fidelity. His recent work spans structural health monitoring, fluid dynamics, and spatial transcriptomics, and he introduced PHLieNet, a hypernetwork approach that conditions forecasts on system parameters for robust generalization. Pantelis combines deep expertise in Python and PyTorch with a track record of translating theoretical advances into adaptive, real-time surrogate models and uncertainty-aware tools. He has bridged academia and industry as Head of Machine Learning at AI2C and through collaborations at Harvard SEAS, often focusing on interpretability and the mechanics of why architectures like gating and attention improve forecasting. Outside core ML, his background in control and optimization (TU München, DLR) informs his practical approach to building deployable, physics-informed solutions.
8 years of coding experience
6 years of employment as a software developer
Master of Science (M.Sc.), Electrical, Electronics and Communications Engineering, GPA: 1.0/1.0, Master of Science (M.Sc.), Electrical, Electronics and Communications Engineering, GPA: 1.0/1.0 at Technical University MunichMaster’s in Science, Technology, and Society (STS), Science, Technology and Society (STS), Master’s in Science, Technology, and Society (STS), Science, Technology and Society (STS) at National Kapodistrian University of AthensBachelor of Science (B.Sc.), Electrical, Electronics and Communications Engineering, GPA: 1.3/1.0, Bachelor of Science (B.Sc.), Electrical, Electronics and Communications Engineering, GPA: 1.3/1.0 at Technische Universität München
German, English, Greek, French
Github Skills (16)
rnn-tensorflow10
backpropagation10
recurrent-neural-networks9
exponent9
gru8
ensembles7
rc7
reservoir7
forecasting7
dynamical-systems7
chaos7
machine-learning5
data-driven5
deep-learning4
pytorch4
Programming languages (1)
Github contributions (5)
cselab/LED
Nov 2021 - Dec 2022
Contributions:18 commits, 14 pushes, 1 branch in 1 year 1 month
pvlachas/RNN-Lyapunov-Spectrum
Jun 2020 - Aug 2020
A data-driven method to calculate the Lyapunov exponent of a dynamical system employing a GRU-RNN.
Contributions:8 commits, 1 PR, 19 pushes in 1 month
data-drivengrurnnrnn-grumethod
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.