SHREYUS PUTHIYAPURAIL

Experienced Software Engineer with a proven track record in creating and executing software solutions for solving complex and multifaceted business challenges. Possess an unbridled passion for Artificial Intelligence with comprehensive knowledge of deep learning, MLOps and related technologies in productionizing the models.

• Deepfake Detection, SJSU, 08/2019, 05/2021, Python, OpenCV, PyTorch, Flask, GCP, Kubernetes, Implemented end-to-end product to identify fake videos and images created using state-of-the-art techniques with an accuracy of 96%. Deployed the deep learning model and web application on GCP using Kubernetes.
• Low Resolution to High Resolution Image Enhancement, SJSU, 08/2020, 05/2021, TensorFlow, TFserving, gRPC, Kubernetes, GCP, Developed the model (GAN) to increase the size of small images while keeping the drop-in quality to minimum or restoring high resolution images from rich details obtained from low resolution images, resulting in 5% better quality.
• Trash Management System using Deep Learning, SJSU, 08/2020, 05/2021, TensorFlow, TFx, Flask, AWS, Created a model to classify 15+ trash objects using image classification and object detection deep learning techniques with 97% accuracy. Implemented TensorFlow extended pipeline for deployment on AWS server.
• Car Rental Web Application, SJSU, 08/2020, 05/2021, Python, Django, Jenkins, CI/CD, Deployed Django web framework-based car rental application using Python. The app affords customers browse and rent cars in different locations based on their availability and price.
• Movie Revenue Prediction using Machine Learning, SJSU, 08/2019, 05/2021, Python, ML libraries, Implemented ML models to predict overall revenue of a movie to be released with 98% accuracy. Scraped and preprocessed movie data for the last 20 years from IMDB and Rotten Tomatoes using Beatifulsoup.