Ernesto Avila-domenech is a data scientist and AI specialist with over a decade of hands-on experience building production-grade LLM systems, RAG pipelines, and OCR-driven document processing for complex, real-world corpora. He combines academic rigor as a PhD student with practical engineering—designing deterministic extraction pipelines, embedding-index strategies, and microservices (FastAPI, ChromaDB, PG-Vector) that turn messy administrative PDFs into searchable knowledge. A founder-in-waiting, he’s currently applying his expertise to public procurement and insurance automation, integrating AWS Bedrock, Textract, and custom chunking to improve semantic search and answer synthesis. Comfortable across the stack—from Python and PyTorch to CI/CD and BI reporting—he has a track record of turning disruptive ideas into tangible SaaS products. Notably, his work emphasizes reproducible, ethically minded language-model solutions and pragmatic engineering choices that prioritize deterministic outputs in otherwise noisy document domains. Based in Spain, he blends research, entrepreneurship, and production experience to solve multilingual, multimodal information challenges.
11 years of coding experience
17 years of employment as a software developer
Master's degree Computer Science, Master's degree Computer Science at Camagüey University
PhD student Computer's science, PhD student Computer's science at Universidad Central “Marta Abreu” de Las Villas (UCLV)
Bachelor's degree Computer and Information Sciences General, Bachelor's degree Computer and Information Sciences General at Informatic Science University, Havana
Contributions:100 commits, 21 PRs, 51 pushes in 2 years 2 months
optimizationjaya
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.