I’m an engineer with a background in robotics, automation, machine learning, and reinforcement learning. I recently transitioned full-time into AI safety, where I’ve been doing research and facilitating AI safety courses with BlueDot.

I’d love to meet more people working in technical AI safety, learn about their research, and better understand where I can contribute most. I’m particularly interested in approaches that try to make AI systems safer by design, reducing the risk of misalignment or dangerous agency.

I’m very happy to help people who are exploring AI safety or trying to find their place in the field. I can share resources, discuss research or career ideas, and connect people with opportunities or others in the community when I can.