Primer on RDF
A quick introduction to RDF and how it can help reduce friction in labor markets.
data scientist statistician builder
For over ten years at the U.S. Department of Labor, I’ve worked at the intersection of data science, software engineering, and federal policy. My work spans the full pipeline: from data engineering and analysis to statistical modeling, forecasting, and deployment.
Put simply, I specialize in solving difficult problems. When a problem requires thinking outside the box, learning something new, or applying unfamiliar technologies and techniques, I draw on methods from statistics, mathematics, computing, and software engineering to build practical, actionable solutions.
I’m particularly interested in problems where computation and statistical methods meet real-world consequences—where a model doesn’t simply describe the world, but helps shape decisions about budgets, strategies, and policy.
Games, notebooks, blogs, and tools — things built for the love of the problem.
A quick introduction to RDF and how it can help reduce friction in labor markets.
A full-featured RDF 1.2 library for Julia with a conformant SPARQL 1.1 and 1.2 engine
A lightweight data validation framework for Julia, designed to help you define, run, and manage data quality checks on tabular data.
A blog focusing on interesting and unique data sources.
Bayesian regression analysis of the incremental effects of educational attainment on income.
A brief primer on Kernel Density Estimation.
Finding career pathways in O*NET data that traditional similarity methods cannot.
A physics-based puzzle game challenging players to navigate a spacecraft through complex gravitational fields using realistic n-body gravitational simulations.
Learn about circle packing by optimizing the size of meatballs! A featured notebook on plutojl.org.
An interactive notebook that clearly demonstrates the fundamental concepts of calculus. Learn and understand limits, continuity, derivatives and integrals in 30 minutes or less.
A crash course in linear algebra.
Clusters U.S. counties within a state according to industrial similarities using k-medoids and fuzzy c-means clustering algorithms.
The travelling salesman problem, as an arcade game. Each level is generated randomly and then solved with simulated annealing.
Leading the development of a department-wide data science and analytics platform, a unified, machine-readable data ecosystem for education and labor via RDF and semantic web technologies, and an MCP server to bridge AI systems with public federal labor data, enabling natural-language access to government datasets.
Architect and deploy production-grade tools across the full data pipeline — from document retrieval systems in Rust (approved for DOL's Certified Software List) to constrained optimization models in JuMP.jl for national labor-allocation problems. Design and execute causal inference studies, Monte Carlo performance models, predictive models, time series modeling, and much more.
Summa Cum Laude · GPA 4.0. Focused on econometric methods and quantitative finance.
Cum Laude · GPA 3.6. Undergraduate degree in Economics with a focus on quantitative methods and econometrics.
If something here piques your interest, let's get in touch!