About

I'm Varun Kotte, a Staff Machine Learning Engineer at Adobe in San Jose. I work on making retrieval and large language model systems reliable enough to sit behind real products.

At Adobe I build the backend LLM-serving and retrieval infrastructure behind AI and search features in six products, including Acrobat, Lightroom, Photoshop, and Express. My work spans the parts of the stack most people don't see: the serving platform, the named-entity recognition behind semantic search, and the reliability layer that decides when a model should be trusted and when it should not.

My focus is calibration, conformal prediction, retrieval that does not hallucinate, and systems that fail honestly. Outside of Adobe I write and publish on these questions, and I'm the first-named of six inventors on a pending patent for closed-domain question answering. I care less about models that impress in a demo and more about ones you can depend on when it matters.