Summary
Arcadio García is an interdisciplinary AI/ML researcher-engineer with 17 years' experience blending probabilistic and symbolic methods to solve challenging problems in bioinformatics and drug discovery. He specializes in probabilistic programming, Bayesian causal inference, stochastic processes and deep latent/state-space models, and brings neuro-symbolic and logic-programming perspectives to graph neural networks and molecular systems. Trained at Oxford, MIT and Cold Spring Harbor Laboratory, he works at the intersection of single-cell epigenetics, TCR–pMHC binding modeling and pharmacodynamics, turning complex biological uncertainty into actionable models. Notably, his work couples differentiable programming (neural ODEs/SDEs) with extreme-value and heavy-tailed theory—an uncommon mix that helps capture rare, high-impact biological events. Based in Oxford, he describes himself succinctly as “Logic & probability,” reflecting a rare combination of formal reasoning and practical probabilistic modeling.
17 years of coding experience
Master of Science, Machine Learning and Statistics, Master of Science, Machine Learning and Statistics at Universidad de Oviedo
Doctor of Philosophy, Doctor of Philosophy at University of Oxford
Probabilistic Programming for Advanced Machine Learning, Probabilistic Programming for Advanced Machine Learning at Massachusetts Institute of Technology
Computational Cell Biology, Computational Cell Biology at Cold Spring Harbor Laboratory
Technical University of Denmark