About
I’m a researcher and software engineer working on mechanistic interpretability and AI safety. At Jinesis AI Lab, University of Toronto, I study how interpretability methods generalize across models and support reliable interventions. My work builds on language-model research at IBM, an MSc in Information Technology from Carnegie Mellon University Africa, and experience developing research tools and software systems.
Experience
Research Assistant, Mechanistic Interpretability
Jinesis AI Lab, University of Toronto
BASE Fellow
BASE Fellowship
Research Fellow
Sentient Futures Project Incubator
Graduate Teaching Assistant, Introduction to Deep Learning
Carnegie Mellon University Africa
AI Research Scientist Intern
IBM Research
Research Assistant
CyLab, Carnegie Mellon University Africa
Co-Founder and AI Software Lead
Anora Breast Cancer Research Foundation
Lead Software Engineer
Caasitech Group LLC
Open-Source Software Engineering Intern (MLH Fellow)
G-Research
Flutter Mobile Developer
Enchird Technologies
