Hi, I’m Sushanti.

I started out as a computer vision engineer and backend developer, back when that was the obvious path into ML. As the field shifted toward NLP, I shifted with it, moving into NLP backend work and MLOps, and from there into machine learning, human-AI simulation, and multi-agent orchestration. That's slowly pulled me toward more systemic and agentic AI, mixing in economics along the way, and more recently into interpretability.

I like building things I wish already existed, usually starting from something I’ve run into in my own life. Right now I'm working on memory and personalization for agents: how they hold on to context, learn the person they're working with, and get better over time. Day to day, I work on applied AI at Adobe.

Before that, I worked across a handful of startups in India, then moved to Berkeley two years ago for my master's. It's been one of the best decisions I've made. California has given me a lot of nature and a lot of sun, and it turns out those might be two of the best things in life.