About Me
I'm an Applied AI Engineer passionate about building intelligent systems that solve real-world problems. I currently work as a Systems Engineer at Tata Consultancy Services (TCS), where I contribute to building AI-driven software solutions. Previously, I worked as a Freelance Machine Learning Engineer , developing AI applications in computer vision and predictive analytics, including an AI-powered Fruit Ripeness Prediction System, an Automated Bottle Detection System, and an intelligent Focus Assistant that recommends personalized neuro-habits to improve productivity.
My core tech stack includes Python, PyTorch, TensorFlow, FastAPI, LangChain, Agentic AI, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), React, Docker, GitHub Actions and FastAPI. I enjoy building complete AI products—from data pipelines and model training to scalable APIs, deployment, and MLOps.
Some of my notable projects include LangGenie, a RAG-powered research assistant that combines LLMs with knowledge retrieved from Wikipedia and arXiv; Bible Chat, an AI assistant that enables semantic Bible search while enriching responses using Wikipedia and real-time web search; and the Automated Amazon Stock Prediction System , which leverages PyTorch LSTMs, a Feature Store, GitHub Actions, and Streamlit to continuously retrain, deploy, and serve next-day stock price forecasts.
Experience
Apr 2025 - Present
Systems Engineer
Tata Consultancy Services
- Working on enterprise applications and AI-driven solutions.
- Collaborated with cross-functional teams to deliver production-ready features.
Feb 2024 – Nov 2024
Freelance Machine Learning Engineer
Remote
- Developed end-to-end machine learning solutions from data preprocessing to deployment.
- Built an AI-powered fruit ripeness prediction system, reducing harvest waste by 25% and improving crop yield optimization by 40%.
- Developed a computer vision–based bottle detection system, increasing recycling processing speed by 20%.
- Built NeuroFocusAssistant, an AI-powered focus coach that diagnoses the root causes of procrastination, distraction, and productivity challenges, providing personalized neurohacks and habit-based interventions.
- Collaborated directly with clients to translate business problems into production-ready AI and machine learning applications.
Education
2020 - 2024
B.Tech in Computer Science & Engineering (AI)
Bharath Institute of Higher Education and Research
CGPA: 8.92 / 10
- Specialization in Artificial Intelligence.
- IBM collaborative curriculum.
- Graduated with a CGPA of 8.92/10.
Projects
VerseChat
An AI-powered Bible Agent that combines semantic search, web search, and Wikipedia retrieval to deliver context-aware answers with persistent conversational history.
- Built an AI-powered Bible assistant using semantic search with PostgreSQL and pgvector for context-aware retrieval.
- Integrated Wikipedia and web search tools to enrich responses with external knowledge.
- Implemented Google Authentication and persistent conversational history for personalized interactions.
- Developed a full-stack application with a React.js frontend and FastAPI backend using LangChain orchestration.
LangGenie
A full-stack AI assistant that combines Retrieval-Augmented Generation (RAG), external knowledge retrieval, and AI-powered content generation for research and writing tasks.
- Implemented Retrieval-Augmented Generation (RAG) using LangChain, pgvector and HuggingFaceEmbeddings for context-aware responses.
- Integrated Wikipedia and ArXiv tools to enhance answers with external knowledge retrieval.
- Built AI-powered writing tools capable of generating essays, blogs, speeches, and other long-form content.
- Developed a full-stack application with a React.js frontend and FastAPI backend, containerized using Docker.
Hourly Amazon Stock Prediction
An end-to-end MLOps pipeline for hourly Amazon stock price prediction, automating data ingestion, feature engineering, model training, deployment, and continuous retraining.
- Designed and implemented an end-to-end machine learning pipeline covering data ingestion, feature engineering, training, inference, deployment, and monitoring.
- Built an LSTM-based forecasting model in PyTorch using technical indicators such as RSI and CCI for time-series prediction.
- Automated daily feature engineering and inference pipelines with scheduled GitHub Actions workflows, alongside weekly model retraining.
- Leveraged Hopsworks Feature Store for versioned feature management, reproducible training, and consistent online/offline feature serving.
- Deployed an interactive Streamlit dashboard for real-time prediction visualization and model inference.
