Projects

Selected work.

A mix of production ML systems, research prototypes, and open-source contributions.

Full-stack AI web app @ Delta Cubes

Recruitment Management System

An AI-powered recruitment platform with resume parsing and job–candidate matching. React.js frontend, Node.js + Express REST APIs, PostgreSQL, and OpenAI API for intelligent candidate understanding and recommendation.

React.jsNode.jsPostgreSQLOpenAI APILLMs

LLM agents · CrewAI · OpenAI

Multi-Agent Deep Research System

An AI multi-agent system for automated web research, data retrieval and report generation. Built agent-collaboration workflows using LLM APIs and a tool-calling architecture; deployed on Windows and Linux.

CrewAIOpenAILangChainPythonMulti-Agent

Deep learning · CNN + LSTM

Speech Emotion Recognition

A hybrid CNN + LSTM model for real-time emotion detection from voice. Extracted MFCC audio features from voice datasets and tuned the model for strong classification performance across emotion categories.

PyTorchCNNLSTMAudioMFCC

Multi-agent video insights

YouTube Trend Analysis

A tool that scrapes YouTube channels and uses multi-agent AI to identify key topics and trends. Shipped as a Streamlit web app for interactive trend visualisation.

CrewAIBright DataStreamlitPython

Applied ML · AICTE Virtual Internship

Crop & Fertilizer Recommendation

An ML model recommending optimal crops and fertilizers from soil and climate data. Applied supervised learning with Python and Scikit-learn, deployed via Streamlit.

Scikit-learnPythonSQLStreamlit

Computer vision @ Infosys

Facial Recognition & Recommendation

A computer-vision facial recognition and recommendation system built with Python and OpenCV. Preprocessing plus deep-learning feature-extraction pipelines exposed via REST APIs to a web UI.

OpenCVPythonDeep LearningREST APIs