I'm a data and ML engineer with 4+ years of experience building production pipelines and deploying ML systems. I hold a Master's in AI for Science from AIMS South Africa / UCT, fully funded by Google DeepMind (2% acceptance rate), where my thesis focused on context-aware neural networks for the ARC-AGI benchmark. My undergraduate thesis investigated adversarial attacks on neural networks.

I'm currently transitioning into technical AI safety research, specifically mechanistic interpretability with a focus on detecting deceptive behaviors in LLMs. I'm seeking funding to conduct 6 months of independent research in Kigali, Rwanda, as sustained work is not currently possible in Sudan due to active armed conflict.

I have won multiple AI competitions including 1st place at the Build with AI Hackathon (Kigali, 2025) and 1st place at the Qeen.AI Data Science Challenge (Qatar, 2025).