Summary
Josh Deetz is a Principal Data Scientist with a PhD in Chemical Engineering and eight years of industry experience applying machine learning to manufacturing and materials problems. He has driven measurable impact—reducing quoted print time errors by 85%, cutting process variation by 35%, and implementing real-time monitoring and anomaly detection pipelines in production. Josh blends deep research chops (eight publications in computational chemistry and postdoc experience) with hands-on ML engineering, deploying models with Docker, Airflow, PySpark, and observability via Grafana. He’s built tools and dashboards that democratize data across organizations and led initiatives to improve data literacy. Based in Fremont, CA, he has a track record of turning atomistic simulations and scientific insight into deployable predictive systems that improve hardware reliability and manufacturing yield.
7 years of coding experience
7 years of employment as a software developer
Doctor of Philosophy (PhD) Chemical Engineering, Doctor of Philosophy (PhD) Chemical Engineering at University of California, Davis