Projects

A curated collection of data engineering and AI-focused projects I’ve worked on — highlighting end-to-end systems, MLOps, and real-time capabilities.

📈 Stock Market Prediction using NLP + GenAI

A hybrid LLM-based system combining stock price data, sentiment analysis, and technical indicators to forecast market movements. Real-time streaming with Redis and FastAPI, and model fine-tuning using Hugging Face Transformers.

Python · FastAPI · Redis · LLMs · Hugging Face · TimescaleDB

⚙️ Real-time ETL Platform with Snowflake

Built scalable ELT pipelines using Python, dbt, and Snowflake to process TB-scale data. Integrated Control-M for orchestration and implemented observability for 1000+ jobs.

Python · dbt · Snowflake · Azure · Control-M

💬 Resume Chatbot powered by LLM + RAG

Developed a chatbot to answer questions about my background using Retrieval-Augmented Generation (RAG). Built with LangChain, OpenAI API, and Pinecone vector search.

Next.js · LangChain · Pinecone · OpenAI API

☁️ Cloud-Native Data Lakehouse on AWS

Implemented a serverless data pipeline using AWS Glue, storing transformed data in S3 and Redshift. Visualized key insights using QuickSight dashboards. Monitored and orchestrated flows with Step Functions and CloudWatch.

AWS Glue · S3 · Redshift · Step Functions · Lambda · QuickSight

🧠 MLOps-Enabled Customer Insights Platform on Databricks

Delivered a unified customer platform with Delta Lake and MLflow to handle training, evaluation, versioning, and deployment of churn prediction models. Employed dbt for transformations and automated model retraining.

Databricks · Delta Lake · MLflow · dbt · Spark · Feature Store