Portfolio

Featured Projects

AI evaluation, language data, and workflow automation

AI Model Evaluation: Fact-Grounded Tests for Frontier Models
Industry

AI Model Evaluation: Fact-Grounded Tests for Frontier Models

Designed question-answer evaluation tasks that expose failure modes in frontier AI models, each anchored to a single verifiable fact and checked through a multi-stage peer review.

Prompt Engineering Source Verification Peer QA Workflows
Application Build System: Modular LaTeX & AI Workflow Automation
Personal Project

Application Build System: Modular LaTeX & AI Workflow Automation

A version-controlled LaTeX pipeline that assembles tailored cover letters and application packets from reusable modules, extended with Claude Code agents and skills that check documents for ATS problems and keep the repository clean.

LaTeX (XeLaTeX) Make & latexmk Python Git & GitHub VS Code Claude Code

Research Methods

Qualitative Research

  • Designed and conducted linguistic fieldwork with Puerto Rican Spanish speakers in Puerto Rico and Louisiana.

  • Developed interview protocols for exploratory research and hypothesis testing.

Quantitative Analysis

  • Designed online studies, coded linguistic variables, extracted datasets, and conducted statistical analysis of sociolinguistic data.

  • Served as Course Facilitator for a graduate Quantitative Methods in Linguistics course at Boston University, covering hypothesis testing through mixed-effects regression; reviewed students’ R analyses and gave detailed written feedback.

Technical Toolkit

Data & Analysis

R
Python
Regex
Excel / Google Sheets

Research & Experimentation

Qualtrics
Prolific

Workflow & Version Control

Git
GitHub
Bash / Terminal
VS Code
Claude
Claude Code

Web & Documentation

HTML
Markdown
HugoBlox

Linguistic & Research Tools

Praat
ELAN
LaTeX

Let's Connect

Interested in working together? Here's where to find my résumé, my code, and how to reach me.