Summary
Ross Johnstone is a data scientist with a decade of experience applying Bayesian statistics, algorithm design, and Python-based scientific tooling to real-world problems across e-commerce, AI-driven drug discovery, and cardiac safety modelling. He holds a DPhil in Computational Biology and an MMath from Oxford, where his thesis developed uncertainty-aware cardiac electrophysiology models that propagate screening data through mechanistic simulations. Ross has built prototype recommender systems in production-focused settings and implemented graph deep learning and ML pipelines with PyTorch for drug discovery, combining rigorous probabilistic thinking with practical engineering. Based in Tokyo and currently at PayPay, he brings research-grade statistical methodology to product teams, with a track record of translating complex Bayesian models into deployable software. An uncommon strength is his experience bridging wet-lab electrophysiology experiments and computational models, giving him a nuanced view of data provenance and uncertainty.
10 years of coding experience
5 years of employment as a software developer
DPhil, Computational Biology, DPhil, Computational Biology at University of Oxford
Dame Alice Owen's School
English, French, Spanish, Japanese