About Self
Background & Expertise
Interested in the infrastructure that makes AI systems actually work.
Most of my thinking lately is around agentic systems, not the demos, but what it takes to make them reliable: evaluation, failure modes, and the gap between a compelling prototype and something you can trust in production. I care about both pushing capabilities forward and building the scaffolding to deploy them responsibly.
Education
BSc Data Science & Engineering
UPC Barcelona · 2027
Location
Barcelona, Spain
Open to relocate
Languages
Spanish (Native) Catalan (Native) English (C2) German (B1)
Experience
AI Engineer Intern
Dow Jones
- • Redesigned Factiva's conversational assistant evaluation framework, proposed new metrics and integrated into CI pipeline
- • Built meta-evaluation framework to assess evaluator reliability
- • Contributed to deep research tooling for AI-powered information retrieval
Technical Skills
ML & AI Systems
Python PyTorch LLMs NLP Evaluation Frameworks RAG
Deployment & Infrastructure
Docker AWS CI/CD FastAPI REST APIs Git
Full-Stack Development
React Next.js Astro Node.js Tailwind CSS
Data Engineering
SQL PostgreSQL ETL Pipelines Pandas Data Modeling