Rithwik Bandi

Full Stack & AI Engineer specializing in scalable backend systems, RESTful APIs, and machine learning pipelines. Experienced in building end-to-end applications and real-time data processing solutions, with a strong focus on performance, security, and reliability.

1. May 2027CGPA: 8.8/10

   S R University, Warangal

   B.Tech in Computer Science and Engineering

1. 2025 – Present

   Heart Risk Prediction SystemFull Stack & AI Developer

   • Architected a full-stack AI healthcare system using FastAPI, React, and MongoDB for real-time cardiovascular risk prediction with secure authentication and scalable backend architecture.
   • Designed a machine learning pipeline with feature engineering, preprocessing, and SHAP-based explainability to deliver accurate and interpretable predictions.
2. 2026 – Present

   JobSpace AIFull Stack Developer

   • Built a job application tracking platform with RBAC, session-based authentication, and RESTful APIs using Node.js and MongoDB for structured workflow management.
   • Designed analytics dashboards with MongoDB aggregations to track application trends, response rates, and support data-driven decision-making.

1. GitHub (opens in a new tab)

   Automated Timetable Analyzer

   • Built a data processing pipeline to transform unstructured Excel timetables into structured schedules using FastAPI and React, including parsing, normalization, and data extraction.
   • Developed scheduling algorithms to identify individual and common free time slots across users, and deployed the system via Vercel and Render for real-time usage.
2. Live (opens in a new tab)

   MCU ExplorerMarvelShowCase

   • Developed a production-grade React (TypeScript) application with modular architecture, Context API state management, and optimized UI performance.
   • Implemented CI/CD deployment, responsive design, and performance optimization to ensure fast load times and scalable frontend architecture.
3. Personal Loan Prediction (ANN)

   • Built a deep learning classification model achieving 91.3% accuracy using TensorFlow/Keras with an optimized multi-layer architecture.
   • Applied feature engineering and model optimization to improve prediction accuracy and overall classification performance.

Programming

PythonJavaJavaScript

Databases

MongoDBSQLMySQLSQLite

Frameworks

FastAPINode.jsExpressTensorFlowScikit-learn

Tools

GitGitHubVS Code

ML & AI

Machine LearningDeep LearningSHAPData Analysis

Web

ReactHTMLCSSBootstrapSweetAlert.js

Core CS

Data Structures & AlgorithmsDBMSOperating SystemsCN

1. Microsoft Azure AI Fundamentals (AI-900)

2. AICTE EduSkillsAI-ML Virtual Internship