Data Engineer & Sports Analyst
I build scalable ETL pipelines that turn hundreds of millions of records into production-ready data — and apply the same rigor to sports analytics.
Monterrey, Mexico
Who I Am
I'm a Data Engineer with 4 years of experience designing and operating scalable ETL pipelines and data platforms for enterprises like Chubb, ZF Group, and Johnson Controls. My day-to-day is Python, Spark, Databricks, and the Azure/AWS stack — building medallion-architecture lakehouses and multithreaded pipelines that move hundreds of millions of records reliably.
Off the clock, I bring that same engineering rigor to sports analytics: modeling match data, building metrics, and creating dashboards that make the game easier to read. If it can't be trusted in production, it doesn't ship.
Selected Work
Simulates the entire 2026 FIFA World Cup 500,000 times using an Elo + xG match model, producing win probabilities for every team from group stage through the final.
Reengineered data architecture and ETL behind customer dashboards for BMW and Ford, plus a KPI platform spanning thousands of plants worldwide.
End-to-end data platform powering a claims-fraud detection system: medallion-architecture lakehouse feeding ML models across four global regions.
Automated daily MLB picks system: Python ingests odds, Statcast, and lineup data, runs a proprietary analysis model, and a public dashboard tracks live performance with equity curves and ROI.
Automated pipeline synchronizing supplier lead times from 13 ERP systems across 52 plants, improving forecasting accuracy for Procurement.
Career
Chubb
ZF Group
Johnson Controls
CEMEX
Tecnológico de Monterrey (ITESM)
Databricks · AWS · Microsoft
Get In Touch
Open to data engineering roles and sports analytics collaborations. The fastest way to reach me is email — I read everything.
jgacontact@gmail.com