# Shengliang Xu > Deep Learning @ NVIDIA | OmniML Location: San Jose, California, United States Profile: https://flows.cv/shengliang ## Work Experience ### Engineering, Deep Learning @ NVIDIA Jan 2023 – Present Model and pipeline optimization for large generative models ### Principal Founding Engineer @ OmniML Jan 2022 – Present Deep learning model and pipeline optimization. Acquired by NVIDIA. OmniML empowers users to design, optimize, shrink, and deploy advanced machine learning models to resource-constrained hardware devices, focusing on mobile, automotive, robotics, and IoT applications. OmniML’s AI software technology enables enterprises to produce small, fast, and energy-efficient machine learning models for on- device AI. OmniML solves the mismatch between AI applications and hardware deployments to make AI more accessible everywhere. OmniML was founded in 2021 by Dr. Song Han, MIT EECS Professor and experienced start-up founder, Dr. Di Wu, former Facebook engineer, and Dr. Huizi Mao, co-inventor of the “deep compression” technology coming out of Stanford. ### Software Engineer, Tech Lead, Commerce ML Infra @ Meta Jan 2020 – Jan 2022 | Menlo Park, California, United States Commerce (Marketplace, Shops and Jobs) Machine Learning Infra Systems. ### Principal Software Engineer @ Plus.ai Jan 2018 – Jan 2020 | Cupertino, California, United States Worked on autonmous driving perception algorithms, and on-vehcicle/backend infra systems. ### Staff Engineer, Technical Team Lead, FlashBlade @ Pure Storage Jan 2015 – Jan 2018 | 444 castro street Responsible for technical innovation and development of FlashBlade. One of the major contributors to the flash management subsystem, the HA subsystem, the metadata subsystem and the snapshots subsystem. FlashBlade is an all-flash scale-out distributed file and object storage product designed from the ground up to meet the demands of modern applications. ### Research Assistant/Teaching Assistant @ University of Washington Jan 2010 – Jan 2015 | Greater Seattle Area I co-designed and developed the MyriaX massive parallel computing system, which is the computing engine of the Myria big data management platform (http://myria.cs.washington.edu/) in UW Database Group. The project is open source in Github (https://github.com/uwescience/myria). MyriaX has been deployed in clusters with hundreds of machines and with terabytes of data. The MyriaX system has a standard one-master-many-worker shared nothing architecture. It uses a relational data model. Data processing functionalities are implemented by operators. It has a set of relational data processing operator implementations as well as an interface for user-defined operators. It supports several high level languages, including SQL, Datalog, and a new scripting language MyriaL. Clients compose a description of data processing requirements in any of the languages. The MyriaX system automatically comes up with a physical execution plan and assigns a set of workers to do the computation. It also handles all the low level system problems such as machine and network failures. The Myria platform is a computing infrastructure in use by many scientists in many departments in UW for managing and processing their massive datasets ### Research Intern @ Microsoft Jan 2014 – Jan 2014 Collaborated with Johannes Gehrke and many other Microsoft researchers and developers in the Cloud and Information Services Lab (CISL). We developed a prototype graph search engine for the Office Graph, which is currently a new product (code name Oslo) under development in the Microsoft Office group. ### Research Assistant， APEX Data & Knowledge Management Lab @ Shanghai Jiao Tong University Jan 2007 – Jan 2010 | Shanghai Research master student, proudly advised by Professor Yong Yu. Research leader of the social search team in APEX Data & Knowledge Management Lab. Research focused on data mining / information retrieval in the social Web environment. ### Research Intern @ IBM Jan 2008 – Jan 2008 Conducted research in Web social text mining, including user emotion mining and text search model analysis. Research papers got published in the IEEE ICDM conference, the CIKM conference, and IEEE TKDE journal. ### Research Intern @ IBM Jan 2007 – Jan 2007 Conducted research in modeling Web social tags for personalized Web search. The research efforts got published in the ACM SIGIR conference. Currently it has more than 240 citations. ## Education ### Doctor of Philosophy (Ph.D.) in Computer Science University of Washington ### Master of Philosophy (M.Phil.) in Computer Science University of Washington ### Master of Philosophy (M.Phil.) in Computer Science Shanghai Jiao Tong University ### Bachelor of Engineering (B.Eng.) in Computer Science Shanghai Jiao Tong University ## Contact & Social - LinkedIn: https://linkedin.com/in/shengliangxu --- Source: https://flows.cv/shengliang JSON Resume: https://flows.cv/shengliang/resume.json Last updated: 2026-04-12