PayProtect
On-device multilingual scam detection
An Android scam-detection project connecting multilingual text classification, TensorFlow Lite inference, and warning overlays—all on the device.
4.8 MB reported model size · <20 ms reported inference
Software DeveloperFull-Stack & Applied AI
I focus on AI agents and automation that make everyday work simpler.
Open to full-time roles & paid internships
tldr; learnt by building things on the internet.
I like systems. The kind with sharp edges, hidden state, and a reason to exist.
My focus: full-stack applications, AI agents, and automation with Python and TypeScript.
My work spans Rasa chatbots, TensorFlow Lite inference, and real-time applications. I’ve also fine-tuned a LLaMA model at the AMD AI Sprint.
I care about making hard things feel simple.
Honours in Artificial Intelligence & Machine Learning · CGPA: 8.45
On-device multilingual scam detection
An Android scam-detection project connecting multilingual text classification, TensorFlow Lite inference, and warning overlays—all on the device.
4.8 MB reported model size · <20 ms reported inference
Rasa-based health-information chatbot
A conversational AI prototype connecting Rasa intent classification and Python actions to a browser chat interface through a REST webhook.
9 declared intents · 2 custom actions
Real-time multiplayer game platform
A browser game platform with server-managed multiplayer rooms, Redis-backed match history, SQLite leaderboards, and WebRTC voice signaling.
3 registered game modes · 8 configured players / room
UI development & integration support
Developed the user interface and helped with integration for a deepfake detection project with Purdue University Fort Wayne, USA.
Software Engineering Intern
RemoteFull-stack development
www.zofatech.inWeb Development Intern
RemoteFrontend development
prodigyinfotech.devFine-tuned a LLaMA model on an AMD MI300X GPU during the AMD AI Sprint.
Published research on sleep apnea detection using deep learning at INCET 2025.
Built Clinico, a healthcare platform, including its UI/UX and ML interface, during a 12-hour hackathon.
Awarded second prize in the Oscillation Research Paper Presentation Competition.