I build AI systems that run without internet, without GPUs, and without paid APIs — based in Dhaka, Bangladesh.
I build AI systems that work where most fail: no internet, no GPU, no paid APIs.
Right now that means
LocalMind AI
(a fully private self-hosted LLM platform with voice I/O and RAG over PDFs)
and
Head Tracking & Blink Detection
(hands-free mouse control for motor-disabled users using just a webcam).
I also ship full-stack AI apps you can try live:
KrishiBot
(an offline-first crop disease assistant in English & বাংলা),
AI Research Workspace
(a streaming research assistant with a 3D topic graph),
GradPilot AI
(a study-abroad platform with an AI advisor),
Wallet Agent
(a Taka expense tracker with an AI assistant),
Financial AI Agent
(sourced stock answers from an NLP pipeline and an LLM agent),
and
Movie Explorer AI
(movie search with personal favourites in Firebase).
I recently completed a remote AI engineering internship at FlyRank, where I built Movie Explorer AI.
Most of my work sits where local LLMs meet real constraints — what it actually
takes to run inference on CPU, build RAG pipelines without a vector database
subscription, and ship accessibility tools to users who can't afford the cloud.
I work mostly in Python, FastAPI, Next.js, and React Native, with OpenCV, LangChain,
and Llama 3 via Ollama underneath.
I write about what breaks along the way — deployment failures, RAG quirks,
and the gap between a working demo and a working product.