Meng Cao - 曹勐

I am a Research Scientist at Google DeepMind. I earned my Ph.D. in Computer Science from Quebec AI Institute (Mila) and McGill University, where I was supervised by Prof. Jackie Chi Kit Cheung. I was also a member of the Reasoning and Learning (RL) Lab.

My research focuses on reinforcement learning for large language models, with a particular interest in agentic reasoning and coding. More broadly, I am interested in developing capable and reliable language-model agents that can reason, plan, coding, use tools, and interact with complex environments. During my Ph.D., I interned at Google Research (Mountain View), Microsoft Research (Montréal), and Borealis AI (Toronto).

For more information, please see my CV here.