News and Updates
🎉 Started PhD at George Mason University CS with a Graduate Teaching Assistantship! (08/2025)
🎉 Promoted to SDE 2 at IQVIA! Grateful for the team's incredible support. (04/2025)
About me
Hi, I am a first-year CS PhD student at George Mason University. My current research focuses on mechanistic interpretability and AI agents — understanding the internal mechanisms of language models and building agentic systems that leverage those insights. I am broadly interested in the explainability and reasoning capabilities of LLMs, as well as safety and bias in AI.
At GMU, I am advised by Prof. Ziyu Yao. In our recent work, we study whether language model agents can serve as helpful circuit explainers in mechanistic interpretability — read our preprint Can Language Model Agents be Helpful Circuit Explainers in Mechanistic Interpretability?.
My undergraduate thesis was under Dr Rifat Shahriyar. In
the thesis, our goal was to detect gender bias in Bangla Language Models. Based on our thesis work,
we have published a paper
titled
An Empirical Study on the Characteristics of Bias upon Context Length Variation for Bangla
which was accepted for poster presentation in the Findings of ACL
2024.