Hands-on machine learning research scientist specializing in surrogate modeling, physics-inspired machine learning for high-dimensional, sparse-data problems.
Built the core algorithm of SModelS (adopted by 20+ international research groups).
Debugged a field-wide error in dark matter simulations, and designed adaptive MCMC pipelines that cut runtime by 10x.
Delivered 30+ international keynotes talks and 60+ particle physics papers in top-tier journals.
2D diagnostic landscape combining reconstruction and physics loss to classify 9 anomaly types without labeled anomalies. Physics-informed kNN outperforms standard baseline by 21 pp on detection rate. Decision framework documented in a 10-part public series reaching 50k+ impressions.
Physics-grounded feature engineering — condition-normalized sensors (KMeans, 6 clusters), rolling statistics, monotone RUL constraint — combined with XGBoost + Optuna tuning. Uncertainty via split conformal prediction (90% coverage). Evaluated on cost-based metrics across all 4 CMAPSS datasets.
Standard VAE collapses to 1D on imbalanced protein data; a differentiable PyTorch GMM penalty recovers all three Ramachandran islands. Latent perturbation across 6 sigma levels confirms 100% win rate in phi stability. Dataset: 1,333–3,335 samples from 5 structurally diverse PDB proteins.
End-to-end technical walkthrough of building a physics-informed LSTM for anomaly classification: architecture choices, the 2D diagnostic loss landscape, and evaluation across 9 anomaly types.
Read on LinkedInWhat the anomaly detection project looks like from a product angle: the decisions made, what the performance improvement actually means operationally, and how physics constraints change the conversation about model trust.
Read on LinkedInBehind the scenes of creating an AI-generated theme song for TEDxGraz: the process, the tools, and what building something creative with ML teaches about its actual capabilities and limits.
Read on LinkedInpen to research leadership roles in scientific ML, physics-informed AI, and computational physical systems. Also available for collaborations and speaking invitations.
