⇾ Conduct research on machine learning, representation learning, and generative modeling applied to protein and antibody systems, with an emphasis on scalable and generalizable model design.
⇾ Designed, trained and fine-tuned protein language models and contrastive representation learning frameworks to capture binding behavior and mutation-driven effects across antibody–antigen pairs.
⇾ Developed structure-aware learning approaches that integrate sequence and 3D structural information, demonstrating improved predictive performance over sequence-only models.
⇾ Built generative and discriminative ML pipelines for antibody interaction modeling, embedding learning, and binding classification across large-scale datasets (500K+ samples).
⇾ Created SPICE, an end-to-end, production-grade web platform for structural protein–protein interaction analysis, enabling comparative analysis of contacts, energetics, and geometric features across variants.
⇾ Published research in peer-reviewed journals, conferences and workshops (JCIM, PLOS, AAAI, NeurIPS) and collaborated with interdisciplinary teams spanning machine learning and computational biology.

⇾ Fine-tuned nucleotide transformer models to predict probe performance in hybrid-capture based cancer detection workflows, validating the feasibility of ML-driven probe optimization.
⇾ Analyzed large-scale experimental sequencing and assay data, translating raw outputs into model-ready representations and performance benchmarks.
⇾ Defined and implemented task-specific evaluation metrics, including sensitivity- and specificity–aware performance measures, to more accurately capture probe effectiveness in hybrid capture mechanisms.
⇾ Trained and evaluated predictive models achieving around 80% accuracy, providing quantitative evidence to support downstream research and future development directions.
⇾ Collaborated closely with interdisciplinary teams across machine learning, experimental biology, and applied research to align modeling assumptions with biological constraints.

Supported instruction for undergraduate courses in "database systems" and "alogrithmic techniques in bioinformatics". Led discussion sections, held office hours, and provided project guidance.

Independently taught core undergraduate CS courses and guiding students through applied ML projects. Courses taught: Programming Language I & II, Discrete Mathematics, Database Management Systems, Operating Systems, Artificial Intelligence.

Independently taught core undergraduate CS courses. Courses taught: Data Structures, Algorithms, Database Systems.