About

Rohith Aralikatti is a skilled Senior Software Engineer (Research) at Samsung R&D Institute Bangalore with over 6 years of relevant experience. His work involves aspects of computer vision and speech recognition, specifically training end-to-end ASR models with both audio and audio-visual modalities as inputs in tensorflow and kaldi, training and deployment of low latency object detection models, deployment of deep learning models on android using tensorflow lite, and implementing pipelines for data cleaning and feature extraction for end-to-end ASR models (for both speech and visual modalities). Prior to joining Samsung, Rohith worked as a Data Science Intern at Goldman Sachs where he predicted the severity of filed IT tickets and possible date of resolution based on a number of parameters and optimized an existing pipeline used for predicting network capacity breach. He also worked as a Research Intern at Tejas Networks where he developed a web tool to optimize the cost of deployment of telecom networks using Django and Python and studied several algorithms for optimization of network deployment cost and implemented a genetic algorithm for the same. He also worked on reducing PAPR in communication systems, which resulted in a patent from USPTO. Rohith completed his Bachelor of Technology in Electrical and Electronics Engineering from the Indian Institute of Technology, Madras in 2017. His tech stack includes Research Scientist, Software Engineer, Tensorflow, Object detection, Computer Vision, Object Detection, Deep Learning, Mobile, Android, Data Scientist, Web, and infra. With his vast experience in the field of computer vision and speech recognition, Rohith is a valuable asset to any team he works with.