A pure Bayesian in education, I spent years building probabilistic models that uncover the latent structure in data. My work focused on methodology and was applied on a plurality of data, from genomics to relational. Most recently, I moved away from methodology driven research and got interested in solving challenges in the real world and most recently in the domain of Health. I constructed models for the prediction of adverse patient outcomes in a hospital. I mostly worked on time-series using probabilistic but also deep learning approaches. I am a firm believer on co-developing the ML models with the users they intend to assist.