Alejandro de la Fuente, PhD
AI engineer, raised on rainforest data and honest error bars.
Hi, I'm Alejandro. My grandfather walked me into the forests of rural Spain as a child, and I never really left the natural world. A decade of quantitative ecology on three continents followed, from pumas in the Andes to possums in Australian rainforest.
I built Bayesian forecasts of wildlife populations, where a wrong number could cost a species its protection. That discipline now drives my work as an AI engineer: explicit assumptions, calibrated uncertainty, and evaluation that finds failure before users do. I like hard problems and tools people actually use.
Bayesian inferencePopulation modellingSystem designAI engineeringEvaluationConservation
- Years of experience
- 10
- Projects
- 16
- Live apps
- 4
- Peer-reviewed papers
- 12
- Citations
- 193
Selected work
-
Digital Twin
A conversational agent answers questions about my work, grounded in a curated knowledge base. A second model reviews every answer before a visitor sees it.
PythonChromaDBGradio
-
7PH Graph
A live knowledge graph of a competitive Magic format: 107 events, 4,591 decks, every chart backed by provenance and statistical guards.
PythonCypherGradio
-
Job Intelligence Engine
An extraction pipeline turns 6,100 job postings into ranked role recommendations. A judge model scores the extraction layer's accuracy.
PythonXGBoostLLM-as-judge
-
Mountains magnify mechanisms
An opinion piece in Nature Climate Change: mountains compress climates into short distances, which makes them natural laboratories for the mechanisms behind climate-driven change.
OpinionClimate changeMountains
-
Physiological stress and possum declines
A model chain from microclimate to physiology to demography showed heat stress and foraging limits driving rainforest possum declines, species by species.
RJAGSBiophysical models
-
Climatic drivers of rainforest bird change
Warming and shifting rainfall drove opposite trends in lowland and upland birds across 47 species. Cyclones and droughts had only marginal effects.
RJAGSRemote sensing