I'm an AI & ML Engineer focused on building production-ready systems — from multi-agent RAG pipelines and computer vision models to scalable backend architectures. I specialize in turning complex ML research into reliable, deployable solutions using Python, TensorFlow, PyTorch, and AWS.
Currently completing my final year of B.Tech (CSE-AIML) at Vignan's Foundation for Science, Technology and Research.
A production-grade medical chatbot powered by a self-correcting RAG pipeline and LangGraph multi-agent orchestration.
- 60% faster query resolution with 95%+ accuracy via autonomous agent routing
- Real-time PII redaction, JWT authentication, and AES encryption for secure data handling
- Supports 500+ concurrent sessions with persistent memory via Redis and PostgreSQL
Python LangGraph Neo4j Redis PostgreSQL RAG NLP · View on GitHub
An enterprise-grade platform for PDF conversion, merging, splitting, compression, and OCR across 15+ file formats.
- 75% reduction in manual document handling using async task queues (Celery) and WebSocket updates
- End-to-end document security with AES-256 encryption, watermarking, and digital signatures
Python Celery Redis WebSockets OCR · View on GitHub
An ML system for cardiovascular risk assessment with clinical-grade interpretability.
- 92%+ ROC-AUC using ensemble models (XGBoost, LightGBM) with Optuna hyperparameter tuning
- 25% boost in minority-class recall via ADASYN oversampling
- SHAP-based feature explanations deployed via FastAPI for clinical use
Python XGBoost LightGBM Optuna SHAP FastAPI
Languages
Python SQL JavaScript TypeScript C HTML/CSS
AI / ML
TensorFlow PyTorch Keras Scikit-learn OpenCV LangChain LangGraph Hugging Face NLP Computer Vision RAG
Cloud & DevOps
AWS (EC2, S3, Lambda) Docker CI/CD GitHub Actions
Databases & Backend
PostgreSQL Redis Neo4j FastAPI Celery
📧 [email protected] | 📞 +91 83096 36226
Open to collaborations, freelance projects, and full-time opportunities in AI/ML.