Skip to content
View Sanjayvk98's full-sized avatar

Achievements

Achievement: YOLO

Achievements

Achievement: YOLO

Block or report Sanjayvk98

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Sanjayvk98/README.md

Hi there, I'm Sanjay V 👋

LinkedIn GitHub

🚀 Software Engineer specializing in Data Engineering, Machine Learning, and End-to-End Data Pipelines.

💡 About Me

  • 🔭 Currently Building: Production-ready MLOps pipelines and Medallion architecture ETL/ELT workflows using Azure, PySpark, and Databricks.
  • 🌱 Learning & Exploring: Advanced Data Engineering patterns, real-time streaming architectures, and cloud data warehousing.
  • 🤝 Open to Collaboration: Data Science, ML/MLOps, and Data Engineering projects.
  • 📫 Reach Me: @Sanjayvk98 on GitHub or via LinkedIn.

🛠 Tech Stack & Tools

  • Languages: Python, SQL, Java
  • Data Engineering & Cloud: PySpark, Azure Databricks, Azure Data Factory, Delta Lake, Azure SQL
  • Data Science & ML: PyTorch, Scikit-Learn, MLflow, LangChain / LangGraph, ChromaDB, Pandas, NumPy
  • Tools & Frameworks: Spring Boot, Git, Docker, Power BI

⚡ Driven by turning raw data into scalable insights and production ML systems.

Pinned Loading

  1. Depression-Tweets-Prediction-NLP- Depression-Tweets-Prediction-NLP- Public

    Sentiment analysis pipeline that classifies tweets as indicative of depression or not, using two complementary models: a fast baseline (TF-IDF + Naive Bayes) and a deep learning model (LSTM with Te…

    Jupyter Notebook 1

  2. End-to-End-Azure-Data-Analytics-ETL-Pipeline End-to-End-Azure-Data-Analytics-ETL-Pipeline Public

    Batch ELT pipeline that ingests raw CRM sales data, transforms it in Spark, and serves it to a Power BI dashboard — built on the Azure free-tier in a one-week sprint.

  3. Spotify-End-to-End-Azure-Data-Engineering-Pipeline Spotify-End-to-End-Azure-Data-Engineering-Pipeline Public

    A metadata-driven, CDC-based Medallion architecture pipeline that ingests a Spotify-style streaming warehouse from Azure SQL, processes it through Bronze → Silver → Gold using Databricks Autoloader…

    Python

  4. Azure-Airline-Loyalty-Churn-End-to-End-MLOps Azure-Airline-Loyalty-Churn-End-to-End-MLOps Public

    An end-to-end system that predicts which airline loyalty program members are at risk of churning, built to mirror a real production pipeline rather than a single notebook: raw relational data → gov…

    Jupyter Notebook

  5. Sp-Stock-500-Forecasting-using-LSTM-Pytorch Sp-Stock-500-Forecasting-using-LSTM-Pytorch Public

    A model bake-off (SARIMA, XGBoost, Prophet, LSTM) for next-day stock return forecasting on S&P 500 data, built on Azure Databricks with a Delta Lake feature store, walk-forward validation, MLflow e…

    Python 1

  6. Chat-with-Document-AI-Assistant-Document-Reader Chat-with-Document-AI-Assistant-Document-Reader Public

    End-to-end PDF RAG chatbot designed to process complex 100+ page documents. Features intelligent LangGraph query routing, hybrid ChromaDB search (BM25 + HuggingFace), and cross-encoder re-ranking t…

    Python