Profile
I build applied AI systems for documents, vision, and operational workflows: spatial OCR, structured extraction, computer vision, and LLM-based workflows. Background in pharma and retail — operational data (SKU, lots, invoices, pharmacy supply chain).
Principle: the LLM orchestrates; deterministic code decides.
Applied AI · LLM systems · Document AI · Computer Vision
Santa Fe, Argentina · open to remote / hybrid
Featured work
-
SupplyMate
Conversational replenishment over a structured catalog. The LLM interprets; Python owns the order quantity. Goldens in CI.
-
Timonel
PaddleX detectors (objects, faces, pose, vehicles) over a single photo. Toggle layers and see what each adds.
-
LexOCR
Academic OCR SPA with PP-OCRv6: spatial boxes, edit, export JSON, Markdown, CSV, or annotated PNG.
-
claimprint
Claims intelligence kernel. Shipped instance: BYMA financial statements. Typed claims are the source of truth; RAG chat is optional.
-
Amanuense
Local demo: PDF or image to Markdown with VLMs via Hugging Face Inference Providers, plus A/B comparison.
Background
-
Pharmaceutical wholesaler, pharmacy channel: operational data (SKU, lots, stock, invoices). Analysis and ML projects on that domain — not generic datasets.
-
Independent AI Engineer — projects and prototypes: SupplyMate, claimprint, Timonel, LexOCR, and Amanuense.
-
Expected graduation from the Tecnicatura Superior in Data Science and Artificial Intelligence at ISTEA (official degree, Argentina).
Demonstrated in projects
- Python
- Docker
- FastAPI
- TypeScript
- Computer Vision
- OCR / Document AI
- LLMs / AI Agents