Euan Baldwin

I'm a First-Class MSc Robotics graduate with a First-Class BSc in Physics, moving into AI safety from a physics and robotics background. My experience includes machine learning, robotics autonomy, verification, and interpretability, and I'm motivated by the challenge of ensuring advanced AI systems are safe, reliable, and beneficial. Alongside my technical work, I was Chair of Effective Altruism Manchester, where I led a growing team and helped build discussion and engagement around AI safety.

I'm seeking opportunities in AI safety where I can apply my background in robotics, physics, and machine learning to reducing risks from advanced AI. My interests include alignment, robustness, interpretability, and AI governance, especially work that combines technical research with practical impact. In the long term, I want to contribute to the safe and responsible development of advanced AI through rigorous, evidence-based work.