I build intelligent systems where AI meets social science — LLM pipelines, RAG-powered conversational agents, multi-agent architectures, and data tools that help research and product teams turn unstructured information into decisions.
I'm an economist and computer-science engineer (M.Sc.) building AI systems for real-world problems. My path is unusual: I started in economics, complex systems, and computational social science, then moved into machine learning and NLP, and now into LLM orchestration, agentic AI, RAG architectures, fine-tuning, and semantic embeddings.
That mix means I do the technical work and understand the social, organizational, and research context behind it. I've shipped conversational agents serving hundreds of users monthly across Latin America, ML clustering pipelines, RAG systems, and dashboards used by research and product teams.
Currently leading data science and AI at Estudio Plural, where I design LLM-based tools for behavioral research, knowledge retrieval, and organizational intelligence. I publish, teach, and consult on applied research projects when there's a good fit.
From production bots to deployed dashboards — a curated set of systems I've built.
End-to-end ML pipeline for archetype discovery. LangGraph orchestrates ingestion → profiling → preprocessing → algorithm selection → clustering → LLM-generated narrative. 33 automated tests passing.
Semantic search over 6 educational documents on gender and parenting. MongoDB vector store + OpenAI embeddings. Multilingual WhatsApp bot with conversation memory in Supabase. 7 specialized agents, 1,544 processed chunks.
Multilingual bot (ES/EN/PT) for Equimundo's A+P Manual. 5 sequential LLM agents: language detection → intent classification → specialized response (factual, planning, ideation, sensitive topics). Built with FastAPI + LangGraph.
Operational monitoring dashboard for the Aly (Apapáchar) WhatsApp bot. KPIs with sparklines and deltas, geographic visualization, alert flags with Excel export and review-status toggle, and a leaderboard with drill-down. Multi-page Streamlit app with custom navigation and i18n.
Automated daily scanner of 15+ funding and grant sources. Claude AI filters by organizational relevance, deduplicates results, and sends curated alerts to Slack. Runs on GitHub Actions every morning.
Interactive dashboard for Colombia's General Royalties System (SGR). Real-time data from datos.gov.co via Socrata API, dynamic filters, choropleth maps, and Excel export. Deployed on Streamlit Cloud.
No-code SaaS platform for building multi-agent chatbots with multi-channel deployment (WhatsApp, Telegram, Web). Full UI in Next.js + shadcn/ui; FastAPI backend with MongoDB Atlas and Supabase auth.
Multi-city survey processing pipeline for social field research across 4 cities in Colombia, Peru, Ecuador, and Bolivia. KoboToolbox integration, validation, deduplication, LLM-generated reports, and 30+ charts for interim deliverables.
Monitoring dashboard for the AMA WhatsApp bot. Tracks user activity, sessions, and engagement across deployments. Streamlit + Supabase backend with Plotly visualizations and Excel exports.
Field-survey validation pipeline for the AMA program in Leticia (Colombia) and Cobija (Bolivia). KoboToolbox QC, ID validation, duration outlier detection per classroom, attendance crosschecks vs Google Forms, school-level Excel reports, and LLM-generated narrative summaries via OpenRouter.
datos.gov.co Open Data API → 8 hours/week saved for the project formulation team.Open to consulting, research collaborations, and new projects — especially where AI, data, and social impact intersect.