Hi, I'm Lisa
Lisa Zhang

Where I am going

AI Interpretability Reinforcement Learning Alignment

Where I have been

Agentic Workflows Distributed Systems

I'm an AI Engineer working toward specializing in LLMs and RL. Currently, I work on building distributed autonomous agents systems at Travelers. Previously, I founded NearMeNow, where I led a team of engineers in developing a real-time, scalable web app to connect people with their nearby social activities.

What am I doing when I'm free? I like to spend time experimenting new tech advances in LLM fields. I currently play around setting up RL environment to try a few techniques for rewarding shaping.

I'm particularly passionate about AI interpretablity, distributed training, and Reinforcement Learning With Human Feedback in the loop.

Projects Overview

View All Projects →

Comparisons of a few RL learning algorithms in the nonstationary bandit setting