About
How I got here, what I work on, and what I’m looking for next.
I grew up in Las Vegas and now split time between there and Washington, DC. I came into college planning to study business and left with two degrees, having figured out somewhere in the middle that the part of business I actually cared about was the data underneath it.
The pivot
I started at Chapman in the Argyros College of Business. The turn came in the quantitative courses, econometrics especially, where the interesting question stopped being what the number was and started being how much we should believe it. I added a second major in data science through the Fowler School of Engineering and graduated in 2025 with both, along with a stint on the Dean’s List and coursework spanning machine learning, artificial intelligence, data structures and algorithms, database management, and the mathematical foundations underneath all of it.
Georgetown was the deliberate next step rather than a default one. The M.S. in Data Science and Analytics let me spend two years on the modeling side without a business-school framing around it, working through probabilistic modeling, statistical learning, neural networks and deep learning, and advanced visualization. I finish in December 2026.
Swimming
Four years on Chapman’s varsity swim and dive team, all four while carrying two majors.
The honest version of what that taught me is unglamorous. Competitive swimming is a sport where you spend an enormous number of hours doing something monotonous, in the dark, before class, for improvements measured in fractions of a second. Nobody watches most of it. The 6 a.m. practices in November are most of what I know about working steadily on hard things, and about the difference between motivation, which comes and goes, and just showing up, which is the thing that actually compounds.
It also taught me something about negative results, which is a theme that shows up in my work. Most training blocks do not produce a personal best. You still have to look at the data honestly and decide what to change.
Work
Between Chapman and Georgetown I spent a year as a data analyst on the Enterprise Alignment team at Mission Support and Test Services, the management and operations contractor for the Nevada National Security Site, supporting NNSA missions.
The work was operational analytics for people who are not analysts. I sat with engineers, physicists, and data scientists to quantify process-efficiency initiatives, which meant translating between what a subject-matter expert knew intuitively and what could actually be measured. That effort documented 400 labor-hours and $600K in annual savings, rolled into the enterprise performance model. I also built Power BI dashboards and automated pipelines for system-performance and reliability metrics.
The lesson from that year was about durability. A dashboard that impresses in a launch meeting and then goes stale is a failure, whatever it looked like on day one. The ones that mattered were the ones people opened on a Monday morning without being asked.
What I work on now
Computer vision on small medical datasets. Curriculum learning, class-imbalance handling, and transfer from related public datasets. My most recent writeup is a negative result on a three-stage YOLOv8 schedule for dental X-rays, which turned out to be a more useful project than a positive result would have been.
Applied statistical modeling. Predicting oral-health outcomes from socioeconomic data, forecasting residential electricity demand from weather, and network analysis of urban delivery logistics. Different domains, same underlying question about what a model can and cannot honestly claim.
A thread runs through most of it. I am drawn to problems where the modeling is only half the work and the other half is understanding the data-generating process well enough to know which results to trust. Survey design in NHANES, class imbalance in medical imaging, simulated demand standing in for records that do not exist publicly. The methods are standard. Knowing where they break is the part that takes judgment.
Outside of that
Still swimming, though nobody is timing me anymore. I read a fair amount of nonfiction, spend time outdoors when DC weather permits and when it does not, and I am a reliable source of opinions about Las Vegas that differ from what you would expect from someone who has only visited.
Looking for
Roles in applied ML, data science, or analytics engineering, starting January 2027.
I am most drawn to work in the public interest, scientific research, or healthcare. My time at the Nevada National Security Site is a large part of why. There is a particular satisfaction in analytics that supports a mission rather than a quarterly target. I am a U.S. citizen and clearance-eligible.
If any of that lines up with what you are building, I would like to hear about it.