Emmanuel Watila
I’m an engineer and AI safety researcher. I started in product engineering, and now build experiments to understand how AI models behave, where they fail, and when they should be uncertain.
I studied Computer Engineering at the University of Maiduguri, where my thesis explored hybrid quantum-classical neural networks. My work spans full-stack engineering, open-source data tooling, and technical writing.
Keywords: Model Interpretability, Model Evaluation, Neuroscience, Physics / Quantum ML
Recent updates
-
Released the preprint Engineer's View of the Brain.
-
Accepted into the Mercial AI Safety Fellowship.
-
Completed the Technical AI Safety cohort at BlueDot Impact.
-
Developed Krisis, a clinical LLM evaluation framework.
-
Founded Readlater, an AI-powered read-it-later platform.
Publications