Research Engineer at Dex -- working on agentic memory, context engineering, and continuous learning. Previously ML Engineer at Adgentic and Senior ML Engineer at Replika, where I worked on post-training, safety alignment, and conversation systems for production LLMs. Here's my CV.

Also into mechanistic interpretability and alignment -- using interp to check if alignment techniques actually work internally, not just behaviorally.

I keep a log of ML notes and annotated implementations.

Outside of work, I play guitar and take photos of random stuff.