Summary
Jay Desai is a Senior Applied Scientist based in Seattle with eight years of experience building ML and sequence models for multimodal emotion recognition and production-grade applied research at Amazon. He brings deep hands-on expertise in TensorFlow/Keras, attention-equipped LSTM/CNN-LSTM architectures, and large-scale feature engineering across audio and video—having built end-to-end models that combined modalities to reach ~80% accuracy in academic projects. Comfortable moving from data collection and database design to model interpretation, Jay has strong practical skills in signal processing tools (Librosa, OpenSmile), computer vision pipelines, and attention-weight analysis to surface regions of interest. Beyond research, he applies quantitative, pattern-driven thinking to nontraditional domains like crypto trading, reflecting a taste for market-based risk management and probabilistic reasoning. Jay pairs an MS in Computer Science with a track record of turning complex, messy datasets into production-ready ML solutions.
7 years of coding experience
8 years of employment as a software developer
Master of Science - MS, Computer Science, Master of Science - MS, Computer Science at New York Institute of Technology
High School, Science, High School, Science at Shree Swaminarayan Acadamy
Bachelor of Engineering (B.E.), Computer Engineering, Bachelor of Engineering (B.E.), Computer Engineering at Savitribai Phule Pune University
English, Hindi, Gujarati, Marathi, Sanskrit