A 2026 B.Tech AI & Data Science graduate who builds AI systems and ships them as working software: an AI form-filling Chrome extension, a fully local voice assistant, a mental health platform used by 100+ students, and offline apps for two small businesses.
Chrome extension that fills web forms with AI from your resume. Every answer must cite a profile field or it is thrown out; 92-check end-to-end suite, released by CI/CD.
Local-first voice assistant for Windows: speech, LLM intent, vision and text-to-speech fully on-device. 29K lines of Python, 125 commands, 849 tests.
Mental health pre-screening for 100+ students, chatbot + PHQ-9/GAD-7 at 95% accuracy, drop-off cut 30%.
Bank statement analyzer, LLM extraction from PDFs and images into structured data, insights via FastAPI + Streamlit.
Leukemia cell classification on C-NMC at 0.90 ROC-AUC, 95% recall; a custom spectral-norm GAN augments scarce data.
Two offline Android apps for real small businesses: a fabrication firm's order tracker and a food stall order board, on relational SQLite.
+ the full set on the portfolio and GitHub ↗
Comparative Analysis of Psychometric Data for Assessing Mental Health Testing Needs Using Machine Learning Models
Benchmarked Logistic Regression, Random Forest, SVM, XGBoost and LightGBM on 28.5K PHQ-9 / GAD-7 records (stratified 5-fold CV, paired t-tests). Logistic Regression led at 99% accuracy with SHAP explanations, and the pre-screening flow roughly halves screening overhead.
Python, Java, JavaScript, TypeScript, Dart, SQL, C++, C, HTML/CSS
PyTorch, TensorFlow, scikit-learn, XGBoost, LightGBM, SHAP, OpenCV, LLMs (OpenAI, Gemini, Claude, Ollama)
FastAPI, Flask, Node.js, Express.js, Next.js, React, Angular, REST APIs, WebSockets, Chrome Extensions
Flutter, Android (Java), Firebase, MySQL, PostgreSQL, MongoDB, SQLite
Git, GitHub Actions (CI/CD), AWS, Pandas, Postman, Google OR-Tools, Unit & E2E Testing, Agile/Scrum
