Saptarshi Sengupta
PhD Student in Informatics
I'm a PhD student at The Pennsylvania State University working on domain-specific applications of LLMs, under the guidance of my advisor, Dr. Suhang Wang. Outside of work, I am an advocate for animal rights 🦙, enjoy reading 📖 (simultaneously on an Alan Turing biography and, fiction - Hunters in the dark), cooking 🍲 and playing the guitar 🎸.
Research Interests
My research interests span various aspects of NLP, including QA, RAG, IR/Search, LLM agents, model interpretability, and low-resource languages. Overall, I'm interested in applying language technologies to challenging edge cases that have either too much/little data. Through my work, I aim to develop methods for tackling real-world problems that are easy to use and cost-effective. You can find my research timeline described in this Google Slide. All of my pre-prints/published work is available on my Google Scholar profile.
Passion Projects
Feed-Forward Neural Network From Scratch
I've always wanted to implement a simple FFNN from scratch just to see how the math works and really understand things at a deeper level. This is my attempt at creating something from an educational perspective, breaking down all the math in bits to be more accessible. Note: All of the code works but some final illustrations remain.
Bengali-English Poetry Translation
I started my NLP journey by working on computational semantics methods applied to Bengali. However, over the course of my MS/PhD, I was unable to extend that work. So, this summer (2026) I took some time to do a passion project - translating Bengali poetry (written by Rabindranath Tagore) to English using an LLM, performing both full-scale SFT and DPO. This was my first time doing DPO and it exposed some very eye-opening realities, all of which I've documented in the readme.
Experience
NLP and Large Language Model Intern
Robert Bosch LLC | May 2025 - August 2025
Performed research in tool retrieval for LLM-agents when dealing with a large number of tools. Proposed a new framework (ToolDreamer) for the same.
Machine Learning Applied Scientist Intern
Splunk | May 2024 - November 2024
Worked on synthetic data generation and LLM-agent trajectory verification for an internal AI assistant. Developed systems were implemented using the Autogen library