Conducting research on Graph Neural Networks (GNNs) using PyTorch Geometric for graph representation learning. Implemented and analyzed Graph Convolutional Networks (GCN), GraphSAGE, and Graph Attention Networks (GAT). Worked on node classification, graph classification, and link prediction tasks using benchmark graph datasets. Developed deep learning pipelines for graph data preprocessing, training, visualization, and model evaluation. Explored explainable AI techniques and advanced graph learning methodologies for research applications.

Worked on large-scale Wikimedia and Wikipedia datasets to support knowledge representation and language technology research. Performed text preprocessing, data cleaning, normalization, tokenization, and corpus preparation for multilingual content. Contributed to the creation and enhancement of structured knowledge resources using Wikidata and Wikimedia projects. Developed Python-based pipelines for extracting, transforming, and analyzing textual data from collaborative knowledge platforms. Assisted in dataset curation, quality assessment, and metadata enrichment for AI-driven language and information retrieval applications. Worked with Natural Language Processing (NLP) workflows involving text analysis, entity extraction, and linguistic resource development. Supported research efforts focused on improving accessibility and usability of open knowledge resources across Indian languages.

Worked on Natural Language Processing (NLP) and Language Technology projects involving multilingual Indian language datasets. Performed data preprocessing, annotation, cleaning, and linguistic analysis for low-resource language applications. Developed Python-based workflows for text processing, corpus preparation, and language resource creation. Contributed to machine learning pipelines for language understanding, classification, and information extraction tasks. Collaborated with researchers to improve data quality and support AI-driven language technologies.