At UOC’s Skills Intelligence Unit, I build large-scale NLP and machine learning pipelines across 10M+ job postings and occupational datasets, extracting and normalizing skills, occupations, and labor-market entities. I develop embedding-based semantic search and RAG systems using BERT and MPNet, alongside LLM pipelines for structured extraction and synthetic-data generation.
I’ve also delivered ETL pipelines, customer-segmentation models, KPI reporting, and analytical tools for Aspasia, Mainjobs, Adecco, Universidad Pablo de Olavide, and ASPAYM Sevilla. My PhD research combined web scraping, topic modeling, clustering, and sentiment-analysis benchmarking, and my applied NLP work includes peer-reviewed research on synthetic data generation.
