Mathematician and 20-year educator. I author mathematics content in LaTeX — full courses, competency-based assessments, standardized-exam items — and build applied AI for education: a retrieval-grounded course assistant with human-in-the-loop feedback tooling, and rubric-based quality gates for assessment. The through-line is measurement — deciding what counts as correct, then holding both student work and AI outputs to that standard.
A few projects that show how I author mathematics content and build the AI and data systems around it — with an emphasis on measurement, correctness, and responsible data handling.
A reusable, config-driven framework for turning any course's materials into an evaluated, privacy-safe RAG assistant — with human-in-the-loop feedback tooling and an evaluation loop. Proven end-to-end on a university capstone.
Two decades of authored math content: nine full university course archives with editable LaTeX source, recent activity-style practice sets, and expository talks with animated slide sequences — Cauchy rigidity, the Art Gallery Theorem, Cantor's infinities.
A live Jupyter Book course site for WGU's Computer Science capstone — task-by-task guidance with complete worked machine-learning examples for classification and regression, used by the students it was built for.
Monte-Carlo existence proofs of how a single aggregate metric can mislead across populations — a literal Simpson's paradox, throughput-driven metric deflation, and non-uniform optimal effort allocation, with symbolic verification.
A Windows desktop app that automates the repetitive Salesforce/Outlook workflow of running a course caseload — batch actions across filtered students, templated email/text, at-rest encryption, a test suite, and a packaged build.
Open-source research software for the creation, manipulation, and display of circle packings (in the sense of Thurston) — tied to my published mathematics on generalized branching.