Graph Machine Learning
Graph neural networks, representation learning, graph autoencoders and unsupervised anomaly detection.

AI · Data Science · Research · Technology
Technology leader, Data Scientist and AI/ML researcher working across Graph Machine Learning, Anomaly Detection, Applied AI and Data Engineering.
Focus
My work spans machine learning research, production analytics, data engineering, enterprise systems and responsible applications of AI. I am especially interested in methods that are technically rigorous and useful in practice.
Graph neural networks, representation learning, graph autoencoders and unsupervised anomaly detection.
Practical AI and analytics systems for decision support, forecasting and data-driven operations.
Reliable data pipelines, analytics engineering and clean integration patterns for enterprise systems.
Selected work
Public, reproducible projects that reflect my research and engineering interests.
Python · Graph MLResearch implementation of graph autoencoder anomaly detection with GAT and MST-geodesic regularization.
Python · AnalyticsClean-room analytics engineering project with synthetic data, validation, dimensional analysis, testing and CI.
Python · Data EngineeringClean-room reference implementation of a synthetic ERP-to-MySQL integration pipeline.