Saurav Panigrahi

I’m a research engineer currently working on LLM post-training and alignment at Zoho Labs.

I am also actively involved in AI safety research. I have worked on self-preservation behaviors in LLMs with Robert McCarthy at UCL, and on value alignment with Jonathan Chang and Prof. Lionel Levine at Cornell. I also contribute to training and evaluation of LLMs in high-stakes domains (medical reasoning) at MEDARC