David Nabergoj
Machine Learning Researcher at University of Ljubljana, Faculty of Computer and Information Science
Ljubljana, Slovenia
Summary
👤
Senior🎓
Top SchoolDavid Nabergoj is a PhD machine learning researcher based in Ljubljana with 10 years of experience building probabilistic and generative models and turning them into production-ready systems. He develops open-source tooling (Torchflows, NFMC) that bridges normalizing flows and MCMC for scalable Bayesian inference, and has applied these techniques across industry projects from Siemens predictive maintenance to time-series forecasting. A competition-driven problem solver, he led a six-person team to win a NASA climate data analysis challenge using geospatial data and has published collaborative work with UC Berkeley. His background spans deep learning, Bayesian statistics, HPC, and deployment (Docker/Singularity/CI), enabling him to move research into operational use. He also mentors students in advanced uncertainty quantification and runs a technical blog on programming, ML, and math, reflecting a habit of explaining complex ideas clearly. Notably, his work mixes theoretical rigor (measure-theoretic probability) with hands-on engineering across Python, PyTorch, Jax, and C++.
10 years of coding experience
2 years of employment as a software developer
Doctor of Science Computer Science, Doctor of Science Computer Science at University of Ljubljana, Faculty of Computer and Information Science
Github Skills (22)
sampling10
cosmology9
bayesian9
density-estimation9
bayesian-inference9
monte-carlo9
generative-model9
python8
mcmc8
astrophysics8
astronomy8
computation8
machine-learning7
inference7
pytorch6
Programming languages (3)
Github contributions (5)
davidnabergoj/potentials
Nov 2023 - Mar 2025
Potential functions for sampling or optimization
Contributions:15 PRs, 75 pushes, 2 branches in 1 year 4 months
davidnabergoj/torchflows
Oct 2023 - Mar 2025
Modern normalizing flows in Python. Simple to use and easily extensible.
Contributions:1 release, 59 PRs, 204 pushes in 1 year 5 months
density-estimationgenerative-modelmachine-learningnormalizing-flowpython
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.