Satyam Upadhyay

I’m a computer applications graduate student (CGPA: 9.12) building strong foundations in data structures, system design, and AI/ML. I enjoy turning messy data into clear insights and then shipping the working models and features that stakeholders can rely on.

In my Machine Learning internship, I used Pandas, NumPy, Matplotlib, Seaborn, and Scikit-learn to analyze, preprocess, and visualize datasets for model building. I performed data cleaning and feature engineering, developed classification and regression models, and evaluated them using train-test split with accuracy and precision-recall metrics.

My projects reflect my preference for practical, production-minded solutions. I built an EV demand forecasting pipeline using Python, TensorFlow, and Scikit-learn, including CNN-LSTM for time-series forecasting and performance comparison across configurations. I also developed a real-time face recognition attendance system using OpenCV with a Tkinter GUI and reliable logging to CSV/SQLite.

I balance ML work with full-stack engineering through a real-time auction platform built with a MERN microservices architecture. I implemented Redis distributed locks to prevent race conditions, used Socket.io rooms for instant bid updates, and integrated BullMQ queues for dependable asynchronous notifications—even under service downtime. I’ve also kept my problem-solving sharp with 140+ LeetCode DSA questions.