Data engineer, clinical AI researcher, and open-source builder.

I'm a data engineer at Egen with 5+ years of experience designing ETL pipelines and cloud-based data systems, and a researcher in clinical AI and graph neural networks. Based in the Greater Chicago area. My day-to-day is mostly Python on Google Cloud (with some AWS), and a lot of thinking about data contracts and reproducible ML pipelines.

I have a master's in Computer Engineering from San Jose State University. I work across data engineering, ML deployment, and cloud architecture, and have collaborated with scientific and medical teams on systems that process structured and unstructured clinical and genomic data at scale.

In 2026, I co-authored and presented research at IEEE ICHI 2026 (Session 16) on an AI-driven early-warning system for predicting multi-organ deterioration in ICU patients. The system uses temporal deep learning with cross-organ attention to flag clinical deterioration a median of 6.2 hours before conventional detection, across five organ systems.

Outside of industry work I maintain open-source Python packages (cloudfit, a cloud-agnostic machine type recommender for batch workloads; clinops, a clinical ML pipeline toolkit; and samplesheet-parser, an Illumina SampleSheet parser), write about data engineering and ML, and publish research. Recent work covers clinical AI for critical care, graph neural networks for drug repurposing, and multi-modal medical image fusion.