I build high-scale data pipelines and cloud architectures that integrate AI into the modern data stack. Focused on automation, data integrity, and turning massive cloud datasets into production-ready intelligence.
| Project | Focus | Tech Stack |
|---|---|---|
| Serverless-AI-Slack-Bot | Real-time Slack integration for automated support. | Python, LLMs, RAG, Slack API (Bolt) |
| Credit Scoring Pipeline | End-to-end Python based data pipeline for financial risk. | Python, LightGBM, PostgreSQL, PySpark, FastAPI, React |
| LLM Conversation Semantic Search Demo | Sample demo showcasing how to productize AI models. | Python, ChromaDB, Microsoft Presidio, Streamlit |
| NLP Playground | [In Progress] An interactive environment for exploring Natural Language Processing techniques. | Python, Spacy, Scikit-Learn, Streamlit |
| 8-Week SQL Challenge | End to end data processing and analysis using advanced SQL (CTEs, Window Functions, Joins, and Subqueries). | PostgreSQL, DBeaver |
Focus: Building reliable, scalable data flows and AI integrations.
- Languages: Python, SQL, Java
- Data & Cloud: AWS (Redshift, DynamoDB, Lambda), PostgreSQL
- AI/ML: RAG Architectures, LLM Fine-tuning, NLP
- Tools: Docker, Git, Pandas, Tableau, Airflow
- Ride-Hailing Ecosystem: Comprehensive Backend and Frontend implementation featuring real-time driver/rider matching.