I build large language models end to end—data curation, pretraining, fine-tuning, and evaluation—with a focus on code generation beyond English, beyond Python, and beyond the benchmarks the field already optimizes for.
I am a Provost's Postdoctoral Fellow at the University of Notre Dame, working with Dr. Joanna C. S. Santos in the S2E Lab on safety-by-construction guardrails and multilingual program synthesis for Code LLMs. I completed my Ph.D. in Computer Science at George Mason University in 2026, advised by Dr. Marcos Zampieri and Dr. Antonios Anastasopoulos. My open releases include mHumanEval, TigerLLM, TigerCoder, and MojoBench.
Code LLMs & program synthesis
Adapting code models to low-resource programming languages and underexplored domains.
Read more →Multilingual & low-resource NLP
Evaluation and modeling across natural languages, with a focus on Bangla and code-mixed text.
Read more →LLM safety & AI in CS education
Guardrails for code assistants and the role of LLMs in introductory computing.
Read more →Benchmarks & datasets
Large, openly released resources that make under-tested settings measurable.
Read more →