David R. Bellamy

Hi there! I am a Deep Learning Scientist/Engineer working at a stealth startup originating from Flagship Pioneering. In my current role, I am developing a physically embodied AI that can conduct experimental science autonomously. My academic work has been featured in top venues such as NeurIPS, the European Journal of Epidemiology, and Nature Medicine. I am also an experienced Python developer and can produce high-quality machine learning code, models and experimental workflows in rapid iteration cycles.

I received my PhD in Epidemiology and Masters in Biostatistics at the Harvard School of Public Health in May 2023 under the supervision of Andrew Beam. In my PhD, I developed Transformer models for risk prediction in the intensive care unit as well as a neural net estimator for causal inference in the presence of unmeasured confounding. Previously, I was a doctoral student at Harvard Medical School in molecular biology and spent 6 years conducting research in epigenetics, mass spectrometry, and virology.

On the causality side, I was a member of the Harvard CAUSALab, where I was privileged to work with and learn from Miguel Hernán and James Robins. I have also consulted with Artera.ai on a causal machine learning project for precision treatment decision-making.

Stemming from my 6 years of experience as a molecular biologist, I have a particular interest in the use of machine learning for drug discovery, protein engineering and the conduct of science more generally.