I come from a small Himalayan village near the Panchachuli peaks in the Kumaon region of Uttarakhand, India . My journey is defined by a leap of faith, leaving my roots to seek new challenges and expand my horizons in the pursuit of professional excellence.

I am deeply passionate about advancing AI in a safe, reliable, and impactful direction. My work lies at the intersection of Trustworthy AI and Adversarial Machine Learning, with a strong focus on modern Large Language Models and their alignment.

Recently, I have been working on understanding how alignment techniques (such as RLHF) can still lead to subtle and targeted failures, especially under distributional shifts or adversarial settings. I am particularly interested in uncovering these weaknesses and using them to improve the robustness and reliability of real-world AI systems.

"I aspire to pursue a PhD focused on LLM safety and alignment, and contribute to building AI systems that are not only powerful, but also reliable and trustworthy in real-world settings."