Hi everyone! I am Saqib, a sixth year Ph.D candidate at department of Computer Science at Stony Brook University, working at the Language Understanding and Reasoning (LUNR) lab under Professor Niranjan Balasubramanian. My research focuses on improving the code generation ability of language models using a plethora of techniques ranging from synthetic teacher distillation to preference optimization. Outside of work, I enjoy exploring the latest advancements in current affairs and the restaurant scene around my current town.
Amazon · Worldwide Returns & ReCommerce
Developed a retrieval-augmented generation system for an LLM-based question-generation module used in customer-facing chatbots. Improved on the production baseline by 7.1% while reducing input and retrieval latency by 73% and 50% respectively.
Amazon · Delivery Experience Speed AI
Built multi-agent LLM pipelines for structured knowledge creation and knowledge-augmented database analysis, reducing person-hour costs for analysis formulation and communication with business stakeholders by 83%.
Bangladesh University of Engineering & Technology (BUET)
Developed deep-learning methods for data-efficient fake-news detection using only 4% of the original training data, and neural compression algorithms achieving 5–35× compression. Received multiple ICT Innovation Fund research grants totalling $36,000.
Stony Brook University
Bangladesh University of Engineering and Technology (BUET)
Built a real-time streamlit application that uses LLM agents and retrieval augmented generation to verify scientific claim validity. The system retrieves relevant scientific documents and generates responses based on the retrieved context.
Analyzed the ability of LLMs pretrained on sequences other than natural language. Observed that LLMs pretrained on structured sequences such as code and scientific reports exhibit stronger performance on downstream tasks compared to those pretrained on natural language.
Developed a novel training methodology that combines weak supervision and active learning to enhance named entity recognition performance with minimal annotated data.
Analysed the various elements affecting the Covid-19 vaccination rates across different counties in the United States. This project involved analyzing vaccination rates using socio-economic variables & tweet sentiment, and developing models to predict future vaccination rates for each county.
Download my complete curriculum vitae for detailed information about my academic background, research experience, and accomplishments.
PDF · Last updated September 2026
Always open to discussing research, collaborations, and new opportunities in NLP.
Department of Computer Science · Stony Brook University · Stony Brook, NY