Ashioya Jotham Victor

I'm a Machine Learning Researcher focused on AI alignment, reasoning mechanisms, and mitigating "hallucinations" in language models. My work explores the intersection of technical AI safety and interpretability, with a particular emphasis on understanding how neural networks encode knowledge and make decisions.

Currently leading partnerships at Google Developer Group (GDG) Pwani and contributing as a technical writer at DataCamp. I hold a BSc in Telecommunications from Kabarak University and actively publish research on AI safety topics. My projects include developing interpretability tools and creating open-source AI alignment resources.