Selected work in AI infrastructure, NLP, and applied research.
AI-powered transcription and analysis pipeline for political focus group research in Mexican Spanish.
A full audio-to-insight pipeline replacing error-prone transcription and weeks of manual coding. Speaker diarization, transcription, theme classification, and integrated reporting — all surfaced through a tooling layer that researchers actually use.
Data preprocessing pipeline and LLM fine-tuning infrastructure for Mexican Spanish political analysis.
QLoRA fine-tuning workflow with reproducible training, evaluation, and registry. Built for empirical comparison of base models, prompts, and adapters across a curated benchmark of domain-specific tasks.
Automated participant screening system for qualitative recruitment.
Automated intake pipeline that replaces hours of manual data entry per project. Combines OCR, fraud detection, and socioeconomic classification — so analysts focus on the decisions, not the paperwork.
Streamlined Python library for scraping case data from the Brazilian Supreme Court (STF).
Most of the work above started as someone saying exactly that.
Start a conversation