👋 Hello, I'm

Bruno Ganontha

M.S. Information Technology · CMU Africa, Kigali
AI & Machine Learning Engineer · AI Safety & Alignment

AI & Machine Learning Engineer with a strong background in software engineering. My career focus is AI research — leveraging machine learning to make a significant positive impact on millions of lives. I specialize in AI Safety and alignment, with emphasis on Mechanistic Interpretability: reverse-engineering neural networks to understand their reasoning and enforce safety barriers.

Bruno Ganontha

Research Interests

AI Safety & Alignment
Enforcing safety barriers in AI systems by understanding and steering model behavior at the representation level.
Mechanistic Interpretability
Reverse-engineering neural networks to understand their internal reasoning processes and thought patterns.
Robustness & Adversarial ML
Evaluating model robustness against natural degradations and adversarial attacks to identify and close safety gaps.
Low-Resource NLP
Building reliable NLP systems for African and other low-resource languages, including robust RAG with abstention mechanisms.

Featured Research

Selected projects — view all research →

Recent Posts

Thoughts on interpretability, safety, and ML — view all posts →