About

I am a computer scientist from Cape Town, South Africa. I am currently working as a Machine Learning Engineer and independent AI safety researcher.

I am excited by the rapid advancements in AI systems, but concerned about the catastrophic risks they may pose. Therefore, I am passionate about exploring AI safety, interpretability, and alignment in my future research to ensure that AI benefits all humanity.

Recent Activity:

• Apr 2025 - Present: Working as a Research Engineer at AI Safety South Africa, measuring the adaptability of LLM agents as a proxy for real-world performance — in collaboration with the Science of Evaluations team at the UK AI Security Institute and funded by the UK AISI Challenge Fund.
• Apr 2026: Teaching assistant for the ML4Good AI safety bootcamp.
• Mar 2025 - Present: Working on the “Precursors to Dangerous Capabilities in AI Agents” project with Leo Hyams and Sam Brown, which led to a poster, “Precursors, Proxies, and Predictive Models for Long-Horizon Tasks”, at the NeurIPS 2025 LLM Evaluation Workshop.
• Jan - Mar 2025: Worked with AI Safety Engineering Taskforce as part of the UK AI Security Institute Bounty program for developing novel AI agent evaluations.

Background and History

I did my Master’s in Computer Science at Stellenbosch University under Marcel Dunaiski. My thesis focused on transformer-based language models for natural language processing tasks. Before that I studied Mathematics and Computer Science at Stellenbosch University.

Other Interests

Apart from working on AI, I enjoy:

• Reading
• Running, Cycling, and Hiking
• Traveling