Hi, I'm Meena Shanmugam

Data Engineering • NLP • Cloud • AI

Welcome to my data engineering and AI portfolio, where I showcase my real-world experience across data ingestion, ETL pipelines, real-time analytics, and applied AI. My work includes my Quvia Experience with Maritime and Aviation data pipeline case studies, hands-on cloud deployments, and end-to-end data workflows. I have also gained industry exposure through my roles at Quvia and Tata Communications, where I contributed to data analysis, automation, and scalable solution development. In parallel, my MSc Data Science Dissertation focuses on legal document summarization and clause classification using transformer-based NLP models, combining research-driven insights with practical AI applications.

A selection of my work in Data Engineering, NLP, Cloud, and AI.

CUAD Clause Classification

Transformer-based multi-label clause classification using the CUAD dataset. Built a custom dataset pipeline, trained LegalBERT, analyzed clause-level F1 performance, and performed legal error analysis.

Hybrid Legal Summarization (Extractive + Abstractive)

Developed a hybrid summarization pipeline combining TextRank for extractive summaries and PEGASUS/T5 for abstractive refinement. Evaluated using ROUGE, BLEU, METEOR, and BERTScore.

Cloud Computing Coursework (GCP – BigQuery, Cloud Run, ETL Pipelines)

Implemented cloud-native data processing pipelines using Google Cloud. Built APIs on Cloud Run, executed scalable SQL transformations in BigQuery, and created dashboards for gender analysis and purchase prediction insights. Demonstrated end-to-end cloud architecture and deployment workflows.