I build backend systems and data pipelines that are reliable, maintainable, and production‑ready. My core interests: clean architecture, ML engineering, and distributed systems.
- 🌱 Deepening expertise in Go, Apache Spark, and NLP
- 🤝 Open to backend & data internships and collaborative projects
|
Languages |
Frameworks |
Databases |
Infra & Tools |
ML & Data |
| Project | Description | Tech |
|---|---|---|
| Fraud Detection System | Production‑ready fraud detection with LightGBM, SHAP explainability, real‑time inference (FastAPI), and Streamlit dashboard. | LightGBM, SHAP, FastAPI, Streamlit, Docker |
| Order Management System | Distributed restaurant order management in Go — orders, inventory, sales analytics, clean architecture. | Go, PostgreSQL, Docker, REST |
| Healthcare AI assistant | End-to-end Deep Learning pipeline for medical text classification, chest X-ray analysis, generative AI, deployment optimization, and responsible AI. | scikit‑learn, deep learning, LSTM |
| Customer Churn Prediction | Distributed ML pipeline on Amazon EMR with Spark ML — feature engineering, model training, ablation study. | PySpark, EMR, MLlib, S3 |
| Transport Complaints Classifier | NLP classifier for public transport feedback using Logistic Regression with visualisations. | scikit‑learn, NLTK, matplotlib, Pandas |
🔗 All repositories — includes Go microservices, Markov chains, credit card tools, and e‑commerce backends.


