Data Engineer | AI & Analytics | MS in Information Systems @ Northeastern University

Welcome to my GitHub! I’m a data engineer passionate about building scalable pipelines, analytics systems, and AI-driven applications. I love working at the intersection of data engineering, ML, and cloud, turning raw information into reliable, actionable, and intelligent systems.

• 🎓 I’m currently pursuing my Master’s in Information Systems at Northeastern University, Boston (Dec 2025)
• 💼 Previously worked as:
  • Data Analyst Co-op at Boehringer Ingelheim - Built Tableau dashboards, automated data pipelines, and improved data quality across large-scale healthcare campaigns.
  • Data Engineer at LTIMindtree - Engineered scalable data pipelines and optimized analytics workflows to deliver reliable insights.
• 🤖 Currently exploring GenAI, Python agents, RAG systems, and healthcare ML
• 🤝 Open to collaborating on data engineering, AI/ML, BI, and research projects
• 💡 Passionate about building scalable systems and making data accessible, reliable, and impactful

Here are some of my key projects hosted on GitHub:

• AI Healthcare System
  RAG-powered medication query engine integrating medical data ingestion, vector search, and chatbot interaction
  LLAMA • RAG • LangChain • Streamlit • Pinecone • FastAPI • Snowflake • Python • SQL • Beautifulsoup

• Mindaid
  LLM-powered mental health assistant with ML models, RAG search, and a Streamlit app for personalized counseling support
  Falcon-7B • RAG • Streamlit • Pinecone • Docker

• Food Inspection Analysis
  End-to-end BI solution with ETL pipelines, dimensional modeling, and Tableau dashboards
  Azure Data Factory • Snowflake • dimensional Modeling • Tableau • Python • SQL • Alteryx

• Optimizing Returns & Refunds in Supply Chain
  End-to-end OLTP system automating returns, refunds, customer reliability scoring, and exception handling
  OLTP • PL/SQL • ERD/DFD • Oracle Database • Supply Chain Systems • Normalization

• DBT Commercial Analytics Data Model
  Data quality framework using schema validation, tests, and CI/CD for commercial analytics with DBT, Snowflake, data modeling, and GitHub Actions automation
  DBT • Snowflake • Data Modeling • GitHub Actions

• Tableau Data Visualization Portfolio
  Collection of interactive dashboards covering retail, public safety, and food compliance analytics, showcasing end-to-end data storytelling and insight generation
  Tableau • Data Visualization • Analytics • Storytelling

• US Accident Prediction
  ML model predicting accident severity using traffic, weather, and road condition features
  EDA • ML Models • Python

• Sentiment Analysis using LSTM
  Deep learning model classifying Amazon customer reviews using LSTM and distributed training
  NLP • LSTM • Distributed Training (DDP) • Pytorch

Python • SQL • PySpark • Scala • Java • Typescript

Snowflake • Redshift • BigQuery • DynamoDB • Delta Lake

Snowflake • Databricks • Airflow • Kafka • DBT • Pyspark • Flink • Lambda • Azure Datafactory • Alteryx • Docker

PyTorch • TensorFlow • Scikit-learn • LangChain • RAG • NLP • Transformers • OpenAI APIs

Tableau • Power BI • Plotly • Streamlit

AWS • Azure • GCP

• Tableau Certified Desktop Specialist
• AWS Certified Data Engineer Associate
• Snowflake SnowPro Core Certification

Feel free to explore my repositories, and let’s connect to collaborate on data engineering, AI, and impactful analytics.