Data Engineering

Car Sales Data Engineering Pipeline

End-to-end ETL pipeline for automotive sales data using Azure Data Factory and Databricks. Performed transformations with PySpark and stored curated Delta tables in Delta Lake for analytics.

Stack: Azure Data Factory, Azure Databricks, PySpark, Delta Lake, SQL

View on GitHub

ETL Data Modeling Business Insights

Machine Learning

Amazon Prime Video Data Analysis & ML Insights

Performed EDA and visualization on Amazon Prime Video dataset. Built ML models to analyze content distribution, trends, and platform insights. Includes charts, graphs, and ML model outputs.

Stack: Python, Jupyter Notebook, Pandas, Matplotlib, Seaborn, ML

View on LinkedIn

Visualization EDA ML Modeling

Applied AI

RAG-Driven PDF Intelligence Assistant

Built a Retrieval-Augmented Generation (RAG) system that ingests PDFs, generates embeddings, and retrieves context-aware answers using FAISS, LangChain, and Groq LLMs.

Stack: Python, LangChain, FAISS, Groq LLM, Sentence Transformers

View on GitHub

RAG LLM Apps Vector Search

Machine Learning

End-to-End ML Project

Built an end-to-end machine learning pipeline including preprocessing, model training, evaluation, experiment tracking, and deployment-ready structure.

Stack: Python, Scikit-learn, Pandas, ML Pipeline, Azure ML

View on GitHub

ML Pipeline Model Training Deployment Ready