About

I am an engineer working across AI systems, research engineering, and AI safety.

My work has ranged from database autotuning with reinforcement learning to LLM post-training and alignment at Zoho Labs. I am especially interested in how model behavior changes under training, how systems should be evaluated, how tools affect reliability, and how failures surface in high-stakes settings.

I have also worked on AI safety research with Robert McCarthy at UCL and Lionel Levine and Jonathan Chang at Cornell, with a focus on self-preservation propensity, emergent misalignment, normative drift, and the side effects of character training.

Alongside this, I have contributed to training and evaluation work for high-stakes domains like medical reasoning at MEDARC.

I am also studying synthetic biology and bioinformatics, with a focus on the infrastructure that connects digital biological design to physical validation. More broadly, I am interested in how reliable AI systems can be applied to programmable biology.

I am happy to hear from people working on AI safety, evaluation, research engineering, medical AI, or programmable biology.