I am a Research Scientist & Member of Technical Staff at Anthropic, working on building safe, reliable and steerable general AI systems.
I have finished my PhD at Stanford University with Prof Surya Ganguli at the Neural Dynamics and Computation Lab as an OpenPhil AI Fellow.
Before that, I was a Google AI Resident working on understanding deep learning, and a Research Scientist Intern at DeepMind working on scaling up theoretical insights, robustness, and out-of-distribution behavior.
During my year at Google Research, I started and led 5 research projects collaborating with scientists from Google Brain and DeepMind.
My research spans machine learning, AI, and physics. I focus on 1) developing the Science of Deep Learning (a principled, scientific understanding of deep learning), 2) large language models and scaling, and 3) applying ML to quantum and astrophysics problems. I am excited about applications of artificial intelligence and machine learning in physics, emergent phenomena, and the role of complexity and openendedness.
I completed my Bachelors and Masters (Part III of the Tripos) at Trinity College, University of Cambridge, and another Masters at Stanford University.
In the past I worked at Institute of Astronomy on galaxy clusters in X-ray, Albert Einstein Institute on large scale data mining for pulsar discovery, Perimeter Institute for Theoretical Physics on perturbative approaches to black hole formation in AdS-like geometries, and DAMTP on cross-correlations of gamma-rays and the CMB in the sky.
I actively co-organize and coach at the Czech Astronomy Olympiad, setting problems and preparing students for the IOAA (where I ranked #1 worldwide in 2011). I sometimes lecture at the Czech Physics Olympiad and prepare students for IPhO. I co-organized the 1st and 2nd International Workshop on Astronomy and Astrophysics in Estonia and the Czech Republic. I am also an amateur astrophotographer. I teach at the Discover Summer Academy and mentor at Yoda Mentorship.
I am reviewing for ML/AI conference, including NeurIPS (top 10% of high-scoring reviewers in 2020), ICML, ICLR, AAAI, and many workshops.
On top of my research, I work on a number of side projects in mathematics, physics, and CS.
Twitter / Google Scholar / GitHub / LinkedIn / Blog