Gathoni is a Research Scholar at ILINA and a Researcher at the University of Cape Town African Hub on AI Safety, Peace, and Security. Her primary research focuses on AI manipulation and persuasion risks, particularly the potential for AI systems to influence human beliefs and behavior at scale. Aside from this, her recent work mainly touched on AI safety evaluations and testing for AI manipulation. She has also contributed to the Delphi consensus on AI evaluation practices. Gathoni holds an undergraduate degree in Psychology from United States International University-Africa.