I build production-grade Generative AI architectures that bridge the gap between cloud intelligence and edge reality.
Specializing in RAG pipelines and LLM agents, I integrate advanced reasoning capabilities into complex systems. My background in IoT allows me to extend AI reach from data centers to the physical world.
Deeply inspired by Japanese craftsmanship and minimalist engineering, I strive for code that is as performant as it is elegant. Currently seeking opportunities to contribute to the Tokyo tech ecosystem.
Generative AI Engineer specializing in RAG pipelines, LLM agents, and production-grade AI systems. Pursuing B.Voc in IoT at Dayalbagh Educational Institute, Agra. I build AI applications that go beyond demos—with real backend engineering, containerized deployments, and cloud infrastructure behind every project.
My rare edge: I combine deep GenAI knowledge (RAG, LangChain, Ollama, local LLMs) with real full-stack backend skills (Django, FastAPI, Docker, AWS) and two years of production IoT development. Most AI engineers can’t deploy. Most backend devs can’t build RAG. I do both — and that matters for the Japanese market especially.
Kage Bunshin no Jutsu
Dayalbagh Educational Institute
Dayalbagh Educational Institute
Adaptive learning platform powered by a full RAG pipeline. Generates personalized courses based on user goals and skill level.
Privacy-first chatbot powered by Ollama. Real-time WebSocket conversations with zero cloud dependency — everything runs locally on your hardware.
Hybrid Wi-Fi + LoRa IoT platform deployed in real college laboratories for fault tolerance, real-time MQTT dashboards, and role-based access control.
Gemini-powered PDF/DOCX resume analysis with intelligent NLP feedback. Deployed on AWS EC2 with Docker. Provides structured improvement suggestions.
Real-time security system supporting multiple IP cameras. Instant email alerts with face snapshots via OpenCV and Redis. Scalable multi-camera architecture.