Results-driven Web Developer and Machine Learning Enthusiast with hands-on experience in building responsive, animated websites using HTML, CSS, JavaScript, and GSAP. Skilled in Python, C++, and Java with applied knowledge in Machine Learning using TensorFlow and Scikit-learn. Experienced in building data-driven solutions and contributing to open-source projects. Strong foundation in frontend development, UI/UX, and problem-solving with a focus on clean code and collaboration using Git.
Completion Certificate:
https://drive.google.com/file/d/1hNHQHW1qLBh5e5daZRDSiY3X-P2qK76t/view?usp=sharing
Completion Certificate:
https://drive.google.com/file/d/1aXkO4ZP2IAzVrAxS8vPi2KW5CPtEWtQ6/view?usp=sharing
Web Development: HTML, CSS, JavaScript, Responsive Design, GSAP, Vite, SEO, UI/UX
Machine Learning: TensorFlow, Scikit-learn, Pandas, NumPy, Supervised/Unsupervised Learning
Soft Skills: Communication, Team Collaboration, Problem Solving, Time Management
Tools & Frameworks: VS Code, Nodejs, Express, React
Programming: Python, Java, C, Git, GitHub, Object-Oriented Programming, Firebase, Google Cloud Console
Web Development
Animating Website – Family Golf
Built a responsive, animated website using HTML, CSS, and JavaScript with Vite. Implemented GSAP and ScrollTrigger for smooth scroll-based animations and added interactive UI features for an engaging user experience.
Engineer Attendance Web Application
Developed a GPS-based engineer attendance system with photo verification. Deployed on Firebase Hosting with Authentication, Firestore database integration, and role-based access control using security rules.
Machine learning and deep learning
Movie recommendation system
(Python, Scikit-learn) built a recommendation engine using collaborative and content-based filtering with cosine similarity, achieving approximately 85% accuracy
Handwritten Digit Recognition (Python, TensorFlow)
Developed a CNN for MNIST digit classification with 98.2% test accuracy using regularization and data augmentation.
Diabetes Prediction System (Python, Scikit-learn)
Trained a logistic regression model to predict diabetes risk with 87% precision using cross-validation and hyperparameter tuning.