Nevil Shah
About Nevil Shah
Nevil Shah is a Deep Learning Engineer currently working at RadiusAI, Inc. He has a background in Physics and Astronomy, with experience at various prestigious institutions including ISRO and IISER Mohali.
Work at RadiusAI
Nevil Shah currently serves as a Deep Learning Engineer at RadiusAI, Inc., a position he has held since 2022. In this role, he focuses on developing advanced deep learning models and solutions that enhance the company's capabilities in artificial intelligence applications. His expertise in machine learning and computer vision contributes to the innovative projects undertaken by RadiusAI.
Previous Experience in Deep Learning and Software Development
Before joining RadiusAI, Nevil Shah worked at LightSpeedAI Labs as a Software Architect from 2020 to 2022. He initially joined the organization as a Software Intern in 2020, where he gained foundational experience in software development. His work included optimizing algorithms and enhancing software performance, which laid the groundwork for his subsequent role as an architect.
Educational Background in Physics and Astrophysics
Nevil Shah completed his Bachelor of Science (BS) and Master of Science (MS) degrees at the Indian Institute of Science Education and Research (IISER), Mohali, from 2015 to 2020. His studies focused on Physics, as well as Astronomy and Astrophysics, providing him with a strong foundation in scientific principles and analytical skills that he applies in his engineering work.
Research and Project Experience
Nevil Shah has participated in various research projects throughout his career. He worked as a Project Student at the Indian Institute of Astrophysics in 2017 and at the Indian Institute of Science Education and Research (IISER), Mohali in 2016 and 2019-2020. Additionally, he contributed to the 'Touch the Jovian Moon Contest' as a team member at ISRO from 2017 to 2018, showcasing his involvement in significant scientific initiatives.
Technical Contributions and Innovations
Nevil Shah has made notable contributions to the field of deep learning. He developed a custom pose model based on the YOLO backbone, which improved human pose estimation accuracy. His work includes optimizing PyTorch models with NVIDIA TensorRT for performance enhancements and designing multi-camera tracking systems, demonstrating his proficiency in advanced machine learning techniques.