Saltar al contenido principal

Scientific & Quantitative Work

My technical work is grounded in scientific training: physics, economics, statistical modeling, computational methods, and reproducible measurement.

I use that background to build systems that do more than process data. They help define metrics, test hypotheses, evaluate models, and connect analytical work to real decisions.

Scientific Background​

I hold a PhD in Economics from Scuola Superiore Sant’Anna and a degree in Physics from the University of Buenos Aires.

My research and applied work have focused on:

  • computational economics
  • nonlinear aggregation and micro-to-macro dynamics
  • statistical modeling and inference
  • survey and census data
  • socioeconomic measurement
  • reproducible analytical workflows
PhD thesis site thumbnail
Deployment: PhD Thesis Online
Docusaurus site with chapter structure and quick navigation.

Applied Measurement​

I build reproducible measurement systems that combine survey, census, geospatial, and administrative data.

Examples include:

  • poverty and income indicators from household survey microdata
  • survey-census harmonization workflows
  • geospatial poverty maps and public-facing data products
  • validation checks and reproducible pipelines for socioeconomic analysis
Argentina Poverty Atlas thumbnail
Deployment: Argentina’s Poverty Atlas
Interactive map with high-resolution indicators and a reproducible pipeline.

Quantitative Engineering​

My scientific background shapes how I build software and AI systems.

I care about:

  • defining the right metric before optimizing a model
  • separating measurement from interpretation
  • making experiments reproducible
  • tracking data lineage and assumptions
  • evaluating whether a model improves a real decision, not only a technical score

This is the foundation behind my work in data science, AI systems, and decision infrastructure.