As a Data Scientist at G5, I mine user journeys for insights that power advertising and conversion funnel optimization. I use Spark and Airflow to productionize models capable of crunching through terabytes of user data. I also build interactive Shiny dashboards to provide account managers and sales leaders with statistically-significant performance metrics.

My current side project is to improve my working knowledge of MLOps by learning Docker and Kubernetes. Quora lists data pipelines as one of the top inefficiencies in data science workflows. I’ve worked with Airflow and GCP for ETL and deployment at work, so it’s time to pick up something new. I will be documenting some of my learnings on this blog; the codebase is hosted on GitHub.

In my free time, I am always feeding my music and concert addiction. I backpack when the ground is dry, skate ski when the ground is frozen, and disc golf whenever I can. You can find some of my travel photos on my projects page.