I am a Computational Scientist specializing in applying advanced generative AI methodologies to solve complex, multi-scale design problems. My expertise lies in translating deep scientific challenges into robust, data-driven computational frameworks designed to predict and create novel solutions.

My core focus is on Generative Design, utilizing state-of-the-art generative models such as Flow-based methods and Diffusion models. I apply these techniques within the context of physical constraints, guiding the design process via (implicit) free energy minimization principles. I also have detailed expertise using probabilistic methods, including Variational Inference and Bayesian Active Learning, which are foundational techniques for robust handling of uncertainty and ensuring optimal generalization across high-dimensional design spaces.

My background demonstrates a strong ability to navigate several high-complexity scientific domains. I have a proven record of developing unifying computational frameworks and pioneering the adoption of machine learning in highly regulated fields. My work in structural and molecular design, including the development of de novo protein design pipelines, has prepared me to tackle the multi-scale complexity inherent in the design of novel molecules and functional materials.

I am motivated by difficult, deep problems that reward computational and unconventional thinking, driving me to build the next generation of exciting scientific solutions to our greatest challenges in health, energy, and climate change.