Engineering AI
that ships.
I build AI systems for teams that answer to regulators. I ship them, I run them, and I stand behind what they output.
Madrid, Spain · from August 2026 · EN / FR / PT / ES
Where I've worked.
I work on production AI today. Before that: software engineering and a technology degree.
AI Solutions Consultant → AI Engineer
I joined as an AI solutions consultant and was promoted to AI Engineer. I built AI systems for tax and compliance teams. In that world, every system must keep records of what it did and protect client data — so I build that in from the start.
- Helped build a legal search engine — Legal and Corporate teams validated 94% of its answers
- Cut task time by 30–80% on the workflows I automated
- Trained 1,600+ professionals to use AI in their daily work
Co-founder & AI Engineer
Revisa Master reviews academic manuscripts. I co-founded it, and I am its entire engineering department. I built the review platform end to end and I keep it running. I answer for its uptime, its costs and its output quality — there is no one else to escalate to.
- A review that took an expert six hours now takes fifteen minutes
- Built the funnels and landing pages behind ~90% revenue growth in one quarter
- Every AI call is traced in production, so I can see what the system did and why
Full Stack Developer
Built the company's digital foundation end-to-end — its first institutional website, CRM integrations, and operational automation for commercial and administrative processes.
- Developed the company's first institutional website and digital-presence strategy
- Automated quotation generation and inventory-control workflows
- Built customer-service automation supporting 120%+ revenue growth in the period
Technologist Degree — completed
Full technology degree covering software engineering, systems architecture, databases, and applied AI — completed with a final GPA of 8.8/10. The theoretical foundation under the practical work.
- Programming logic, data structures, and algorithms
- Database design, SQL, and systems architecture
- Web development, APIs, and applied AI
Building production AI is engineering work — not prompting.
A demo is easy. A system that runs every day for a regulated team is hard. The difference is engineering: pipelines that don't break, answers you can audit, and checks that catch the model's mistakes before a client sees them.
That discipline came from practice. I co-founded a platform and I keep it running in production. I built a company's website, CRM integrations and automations, end to end. I finished a systems degree with an 8.8/10 GPA. The AI gets the headlines. The engineering makes it ship.
When something interests me, I go all the way in. In linguistics, that meant graduating top of my cohort at the University of São Paulo (9.2/10 GPA) and earning a merit scholarship to Université Lumière Lyon 2 in France. In technology, it means a systems degree finished with an 8.8/10 GPA, a promotion at KPMG, and a peer-reviewed paper on multi-agent architecture — the same architecture I run in production. I changed fields. The standard stayed.
Four principles I won't compromise on.
Production-first
I architect for the live system, not the demo. The work that survives contact with real users is the work that matters.
Ship to learn
A prototype proves an idea. A running system teaches you what is actually true. So I deploy early and iterate fast.
Multi-agent by default
I split big problems into small agents. Each agent has one job. That makes the system easier to test, debug and explain.
Build for adoption
A system nobody uses is a failed system. I teach the team while I build — not after.