Vansh

Built a GAN-based super-resolution pipeline for satellite thermal imagery using U-Net + PatchGAN, achieving 4× spatial resolution improvement and 30% SSIM gain over baseline models. Processed 78GB of remote-sensing data into 25K+ training patches, optimizing custom loss functions to reduce inference time by 40%.

Artificial Intelligence Intern - Codec Technologies Pvt. Ltd. - Remote

(2025-07 - 2025-10)

• Built a GAN-based super-resolution pipeline for satellite thermal imagery using U-Net + PatchGAN, achieving 4× spatial resolution improvement and 30% SSIM gain over baseline models.
• Processed 78GB of remote-sensing data into 25K+ training patches, optimizing custom loss functions to reduce inference time by 40%.

Data Science and Machine Learning Intern - UniConverge Technologies Pvt. Ltd. - Remote

(2025-12)

• Developed a TensorFlow Lite computer-vision model for real-time plant disease detection on edge devices.
• Integrated weather data (humidity, temperature) via OpenWeatherMap API, improving disease risk prediction F1-score by 15%.

Bachelor of Technology - Computer Science and Engineering - G.L Bajaj Institute of Technology and Management (2027)

Senior Secondary - Class XII - St. Mary's Convent School (2023)