Industrial engineer turned AI researcher.
My background is in optimizing complex industrial systems. I now apply that same rigor to the development and alignment of artificial intelligence.
I believe that Artificial Intelligence is the ultimate industrial engineering problem. It is not just about code; it is about the flow of information, the optimization of decision-making, and the alignment of stochastic outputs with deterministic goals.
Born in Ecuador, currently operating out of Spain. I have spent the last 7 years dissecting systems—from logistics chains to corporate knowledge bases—and rebuilding them to be more efficient, transparent, and resilient.
The Pivot to AI Safety
As LLMs began to demonstrate reasoning capabilities, I realized that the tools I used to debug factories could be used to debug cognition. My research now focuses on:
- Constitutional AI: Embedding normative constraints into model behavior.
- Mechanistic Interpretability: Understanding the "why" behind the accumulation.
- Epistemic Security: Protecting information ecosystems from degradation.