Hi, I'm a Research Engineer. I currently work on AI Safety evaluations, focusing on reward-hacking.
I am broadly interested in causality and trustworthy ML, with an inclination towards empirical research. In the past, I've worked on computer vision for self-driving vehicles, machine learning on the edge, and reinforcement learning.
Open to PhDs!
I'm currently searching for PhDs in ML (specifically in Europe)! Please view my Curriculum Vitae.
Recent News
- I earned my AI Safety Fundamentals (Alignment) Certificate from Bluedot
- I'm joining the Howison Lab at UT
- I'm joining the 11th Edition of AI Safety Camp
- I graduated with M.S.E ECE from UT Austin
- My co-authored paper on Smart Tools was accepted at ASME 2024