Hi, I’m Javier! 👋 I’m a data science leader, open-source evangelist, and machine learning engineer who thrives at the intersection of predictive modeling, experimentation, large-scale AI delivery, and GenAI. My North Star is simple: Solve real problems with data and share the playbook.
Data Science & MLOps
I first honed my data science skills by enhancing valuation and forecasting models with algos like ARIMA and XGBoost. After moving to health tech, I discovered a passion for developing ultra-fast, enterprise-grade Shiny web apps.
Today, I spearhead machine learning and AI initiatives at Centene that enhance healthcare quality and customer experience for over 28 million members. I architect scalable ML solutions, empower junior team members to deliver value-driven software, document best practices, and publish internal packages and tutorials that reach 1,000+ data scientists, analysts, and engineers.
On any given day, you’ll catch me deep in Databricks, Positron (an OSS VS Code fork), RStudio IDE, JupyterHub, Posit Connect, and the Linux CLI wiring together Arrow, DuckDB, model-serving LLM endpoints, data pipelines, and Docker-ized services.
Languages
My daily languages include R, Python, SQL, and Bash, but my preferred language is R. I use R for a wide range of work including ML/AI model development, package creation, communication with data warehouses and REST APIs, vector DB + RAG solutions, automation pipelines, interactive apps, and websites (for example, this site was built with R + Quarto).
Data Science Communities
There are a plethora of online and in-person data science communities to learn from and share your own experiences. Online communities for open-source languages and data science are incredibly welcoming and below are my favorites: