I’m a lead data scientist with over five years in data science and engineering, embedded on a supply chain operations team at a large grocery retailer. “Embedded.” I sit between the business, data software engineers, and statistics PhDs, and speak all of their languages. I design and build the things those people need, from shipment prediction models across 35 distribution centers to document intelligence pipelines to the data infrastructure underneath all of it. If something I do makes the team or the company stronger, it’s a good day.
Before data, I ran continuous improvement at a dairy plant as a Lean Six Sigma Black Belt. That background shows up in how I think about problems. Process first, then tooling. If you can’t draw the workflow on a whiteboard, writing code for it won’t help.
Background
- MS in Statistics, California State University, Fullerton (2020)
- MBA, California State University, Long Beach (2017)
- BS in Mathematics, University of California, Irvine (2012)
- Lean Six Sigma Black Belt
Day to day I work in Python, PySpark, Databricks, and SQL, deploy with Terraform, and track models with MLflow.
Languages: English (native), French (B1+).
What I write about
Projects, mostly. Things I’ve built, things I’ve figured out, things that didn’t work the way I expected. The common thread is probably “we’ve gotten from 0 to 1, how do we get to 1000?” Sometimes that’s a neural net to find Puss in Boots in movie frames. Sometimes it’s six batches of tempeh trying to get the incubation right.
The work stuff I can talk about tends to be at the intersection of ML and operations. Document intelligence, shipment prediction, NLP applied to places you wouldn’t normally think to use it. The personal projects are where I test ideas without a deadline. NLP, food science, Arduino, computer vision.