Welcome!
Hi, I’m Alejandro — AI Engineer and Data Scientist
I build LLM-powered applications and ML systems that turn messy data into outputs people can act on: production RAG pipelines, agentic workflows, and end-to-end analytics built with Python and SQL.
My background is in quantitative ecology and climate-change science, where I built uncertainty-aware models to understand how living systems respond to environmental change. I bring the same rigour to industry: careful assumptions, transparent validation, and decision-ready delivery.
What I build
End-to-end AI and data systems that prioritise reliability and usability:
- RAG systems and LLM applications — retrieval pipelines with evaluation frameworks (MRR, nDCG, LLM-as-judge) and structured output patterns
- ML workflows — from problem framing and feature engineering to model evaluation with transparent trade-offs
- Data pipelines — clean, testable, reproducible pipelines with validation and clear artefacts
- Decision support — results communicated clearly: what changed, why it matters, what to do next
Featured work
Job Intelligence Engine — parses thousands of real data job ads into a skills taxonomy and market signals, then recommends best-fit roles and a prioritised upskilling plan.
- Skill demand & salary signals by role/family
- Best-now vs stretch role job recommendations
- Ranked upskilling priorities (positioning lift)
Stack: Python • NLP embeddings • XGBoost/LightGBM • Streamlit • reproducible pipeline & persisted artefacts • SHAP
See demo & details