Zhengnan Huang
About Zhengnan Huang
Zhengnan Huang is a Software Engineer at Nautilus Labs, specializing in machine learning-based reconstruction models. He holds a PhD in Biomedical Imaging & Technology from New York University and has extensive experience in data processing and deep learning applications.
Work at Nautilus Labs
Zhengnan Huang has been employed at Nautilus Labs as a Software Engineer since 2022. In this role, he is responsible for maintaining a data processing pipeline, which is integral to the company's operations. His work contributes to the efficiency and effectiveness of data handling within the organization, supporting Nautilus Labs' focus on advancing maritime technology.
Education and Expertise
Zhengnan Huang holds a Master of Science (M.S.) in Bioinformatics from the University of Michigan, where he studied from 2015 to 2017. He also earned a Doctor of Philosophy (PhD) in Biomedical Imaging & Technology from New York University, completing his studies in 2023. His undergraduate education includes a Bachelor of Engineering in Bioinformation Technology from Huazhong University of Science and Technology, achieved from 2010 to 2014. His academic background supports his specialization in machine learning-based reconstruction models and convex optimization.
Background
Zhengnan Huang has a diverse professional background in software engineering and research. Prior to his current role, he worked as a Graduate Research Assistant at NYU Langone Health from 2017 to 2022, where he gained significant experience in biomedical imaging. He also served as an Algorithm Engineer at InferVision for two months in 2018, where he developed a deep learning-based automated lesion detection system during his internship.
Technical Skills and Specializations
Zhengnan Huang specializes in machine learning-based reconstruction models, with a particular focus on convex optimization. He has extensive experience with GPU computing, utilizing PyTorch on Linux-based computer clusters. His technical skills are aimed at reducing MR scan and image reconstruction times while maintaining image quality, showcasing his commitment to advancing deep learning methodologies in medical imaging.