AI Engineer with over 10 years building production mobile and streaming systems, now focused on on-device AI — open-source infrastructure for running LLMs and RAG directly on edge devices.
Open to full-time & contract — on-device, self-hosted & cloud AI, plus Android.
The AI library in your pocket — free offline NCERT books that read beautifully, an AI that answers from the book with the exact page, plus quizzes, flashcards and games. Coming to Google Play as a closed pilot.
Reproducible benchmark numbers from a Snapdragon 7 Gen 1 phone and a Snapdragon 870 tablet — measured from inside the app, on the CPU, fully offline. Decode tok/s, time-to-first-token, peak RAM, and RAG latency.
v0.10 is a retrieval release — an optional EmbeddingGemma embedder tiered to your device, hybrid dense + lexical search, a flagship reranker, and a set of grounding fixes that stop the model answering from the wrong file. Still fully local, no account, no upload, no telemetry.
v0.9 teaches the on-device model to answer with charts, makes the UI adapt from phone to tablet, and pulls the whole AI core out of the app into a reusable Kotlin Multiplatform library — still fully local, no account, no upload, no telemetry.
