RAG Query Mail AI
End-to-end AI document processing & Q&A platform — PDF parsing with Surya OCR, PyMuPDF, PyTesseract, LlamaIndex and Qdrant vector DB. Email watcher auto-ingests documents into Qdrant.
Sr Software GenAI Engineer with deep expertise in RAG, LLMs, Computer Vision and OCR — shipping production-grade AI for document intelligence, automation and analytics.


Currently Sr Software Engineer — Gen AI at Indian Tec Solutions, where I build RAG-based document intelligence platforms, AI chatbots, and automated banking & KYC workflows. Published researcher with a track record of transforming messy business problems into production-grade AI systems.
RAG pipelines, LLM apps, LangChain, LlamaIndex, Ollama, OpenAI.
OCR, YOLO, OpenCV — document intelligence at production scale.
TensorFlow, XGBoost, classification & predictive analytics.
AWS EC2/S3, Azure, Docker, FastAPI services in UAT & Prod.
End-to-end AI document processing & Q&A platform — PDF parsing with Surya OCR, PyMuPDF, PyTesseract, LlamaIndex and Qdrant vector DB. Email watcher auto-ingests documents into Qdrant.
ML + OCR pipeline for document classification, Aadhaar masking and super-resolution APIs. TensorFlow, OpenCV, YOLO, NumPy — deployed on AWS.
LangChain + GPT-4o Mini for precise retrieval over complex PDFs. FAISS vector store, OpenAI embeddings, PyMuPDF + PyTesseract OCR for scanned docs.
Intelligent process automation for customer-support email categorization, failure log analysis and API monitoring with auto alerts.
Automated assessment of Banking Bureau Variables to predict loan repayment, with MongoDB-backed pipelines, XGBoost retention models and FastAPI services.
ML-based fraud detection catching tampered financial documents — advanced analytics and AI algorithms reducing fraudulent activity in bank statements.
Published research paper in IJRASET (ISSN 2321-9653, ISRA Impact Factor 7.429) — applying ML & image processing for medical imaging.
R&D for data enrichment and targeting — AI-driven solutions for customer profiling using internal and alternate data sources.

Always happy to talk about RAG, agents, OCR pipelines, and shipping AI products that actually run in production.