cv

NLP Research Intern | XRI Global (Remote)

• Developed a semi-automatic ETL system to guide resource allocation by identifying low-resource languages for machine translation (MT) and structuring multilingual datasets
• Created ML pipeline to improve baseline system (+4 BLEU) using strategies for low-resource languages, such as, back-translation, multilingual transfer, and language identification
• Presented internship work at LT4ALL poster session and contributed to front-end integration of datasets into website

LLM Data Annotator

• Constructed datasets used to evaluate the performance of language models on rhetorical questions and subjectivity; results were submitted for publication (under review) introducing the dataset
• Contributed to documentation quality by producing additional guidelines and incorporating linguistic tests, resulting in a Cohen’s kappa score of 0.66

Community Health Worker/Analyst

• Identified high-risk, disconnected patients by analyzing EHR data and querying clinical databases using Power Query to support strategic outreach and patient engagement outcomes
• Optimized approval workflows to strengthen data integrity and reduce gaps for HEDIS measures
• Standardized the post-discharge pipeline to effectively coordinate home visits and connect patients with essential medical and social services
• Conducted patient interviews to collect clinical data and provided Spanish translation services when needed

Research Assistant

• Conducted and supervised bilingual picture description tasks to analyze grammatical structures (i.e., noun phrases)
• Programmed psycholinguistic experiments in Ibex using JavaScript, HTML, and CSS

M.S. in Human Language Technology

• Computational Linguistics

B.A. in Linguistics

MT on Hub (Hugging Face)

• Submit PRs to update language metadata (e.g., ISO codes) for machine translation datasets
• Correct file errors in uploaded datasets by preprocessing .csv files or starting community discussions

spaCy Industrial-strength NLP

• Contributed to GitHub discussions by examining code bases and citing documentation to provide clear guidance
• Currently implementing additional features to improve support (e.g., update rule set to verify lemmas, expand vocabulary) for the Spanish language

LLMs from Scratch

• Active maintainer that closes issues via PRs (following best-practices), adding unit tests, and enhancing code documentation

Transformers (Hugging Face)

• Translating documentation from English to Spanish and using terminology relevant in the language

Bridging the digital divide Where do we stand?

• Language Technologies for All (LT4All 2025): Advancing Humanism through Language Technologies