About

Arkadeep Das is a skilled Software Engineer with a strong interest in Deep Learning. He is currently working at JPMorgan Chase & Co as a Software Engineer II, where he has designed solutions and order strategies for the Forex/Rates Algo Execution team. He has implemented algorithms to reduce startup and processing time of several critical Algo UI applications and worked towards onboarding existing infrastructure to newly implemented stack. He has used Java, Python, and Advanced Message Processing systems in his work. Prior to his current role, Arkadeep worked as a Mitacs Globalink Research Intern at Simon Fraser University, where he focused on Adversarial attacks in Deep Learning. He used state-of-the-art neural networks, Nasnet-Large and Inception-Renset-v2, for binary classification task of chest X-ray-14 dataset comprising over 0.1 million gray-scale images. He implemented ten different adversarial attacks from three different categories, exposing the vulnerability of deep learning classifiers. Furthermore, he modified the pooling operations in the two classification networks to measure their sensitivities against different attacks, on the specific task of chest X-ray classification and established Nasnet-Large with average pooling as the best network. Arkadeep also worked as a Research & Development Intern at NcFlexe, where he implemented SVM using Gabor Features and Histogram Oriented Gradient as feature descriptor for classifying images of tags as genuine. He used a neural network-based approach of retraining Google inception-net-v3 using transfer learning to implement a deep learning classifier. He also developed software prototypes, worked with DBMS like SQLite and Firebase Realtime Database, and improved on the existing app to make it production-ready. Arkadeep has a Bachelor of Technology (BTech) in Mathematics and Computer Science from the Indian Institute of Technology, Guwahati. He has experience working with various technologies such as Keras, Neo4j, Cassandra, Spring, UI, Neural Networks, Infra, SVM, Web, Microservices, and Spring Boot. With 3.86 years of relevant experience, Arkadeep is a valuable addition to any team that values innovation and expertise in Deep Learning.