About

Abhirav Dilip Kariya is a highly skilled Applied Scientist and Machine Learning Engineer with a passion for Artificial Intelligence, Computer Vision, NLP, and Data Science. With almost 3 years of relevant experience, Abhirav has built an impressive track record in the field of technology. Currently, Abhirav works as a Software Engineer at Amazon, where he applies his expertise in Machine Learning to develop innovative solutions. Prior to this, he worked as a Graduate Research Assistant at the ASSIST Center, where he collaborated with the Crop and Soil Sciences department to model structural changes in cell shape and composition of cotton fibers. He created a cotton fiber tip dataset from microscopic slides using LabelBox for detection and classification of tips from over 3000 raw images. Abhirav also put together a pipeline to localize and classify fiber tips, extract their geometry exploiting YOLOv4 detector and classical computer vision algorithms. He trained unsupervised models like Variational Autoencoders (VAE) to learn latent representation of tips to subsequently observe variation caused by treatments. Abhirav also pioneered a paradigm to detect water stress in plants employing Detectron2 CNN for detection and semantic segmentation of near-infrared (NIR) images. Abhirav has a Master of Science degree in Electrical Engineering from North Carolina State University, where he honed his skills in Probability, Statistics, Algorithms, Data Structures, Object-Oriented Design, and Software Development. He also has a Bachelor's degree in Electronics and Communication Engineering from the International Institute of Information Technology. Abhirav's technical expertise includes Research Scientist, ML, Software Engineer, Computer Vision, NLP, Data Scientist, and CNN. He is a highly motivated and goal-oriented professional with strong problem-solving skills and a passion for innovation. Abhirav is an excellent team player and has a proven track record of delivering high-quality results in a fast-paced and challenging environment.