I’m a computer engineer with a BSc degree in Computer Engineering (IT track) from the University of Oviedo. My background is in AI applied to security: machine-learning systems for intrusion detection in industrial settings prioritizing safety while running under constrained hardware.

I’m now pivoting toward AI safety, working as an ML researcher on the properties that decide whether these systems can be trusted: interpretability, fairness, privacy, and bias.

Interested in these topics or want to know more? Let’s talk!

angel [at] arrospide [dot] dev