# Jianbao (Jim) Tao > Software Engineer@Meta Location: San Jose, California, United States Profile: https://flows.cv/jianbao Experience: 12+ years of backend engineering, ranging from offline data pipelines, to search verticals, and most recently to ads model serving infra (an area of RecSys inference) at Meta. Interest: AI model/software/hardware co-design for training/inference of LLM and RecSys models Skills: CUDA kernel programming, PyTorch C++/Python ## Work Experience ### Staff Software Engineer @ Meta Jan 2022 – Present | Menlo Park, California, United States Jun 2023 - present, Ads ML Serving Platform Scope: Retrieval stage GPU-powered ads models serving. I have a track record of driving major advancements and solving complex engineering challenges in ads model serving infra. Examples: * Design and implemented AED (ad embedding on device). Notable complexities: GPU-based hash table to allow O(10-100k) concurrent lookup, HBM/DRAM hybrid storage for ad embeddings to allow O(100M) ads in memory, vectorized memcpy that is 16x faster than CUDA native memcpy. Impact: alleviated memory bottleneck and CPU bottleneck for major retrieval stage ads models and hence unblocked their launches. AED has become a foundational building block for ads retrieval stage GPU model serving. Without it, several ongoing high-profile projects, such as TorchRetrieval, Neutron Star on AMD, Genre 3.0, and Stage Consolidation, would be blocked. * Major contributor for Neutron Star launch (first GPU-based model serving system in ads serving infra). I served as predictor service TL and solved a few hard problems (eg, invented a novel solution to derisk Manifold IO throttling for NS model serving; mitigated fallback SLA blocker) * The AMD model serving launch in ads retrieval stage model serving. Served as TL and personally solved arguably the hardest problem, which was the CPU bottleneck on AMD. Jan 2022 - May 2023, Metrics Computation Infra ### Staff Software Engineer @ LinkedIn Jan 2018 – Jan 2022 | Sunnyvale, CA 2019-04 to 2022-01: Search, LSS (Tech stack: lucene/java/scala/hadoop/spark/hive/kafka/gradle/git) 2018/10 to 2019-03: Salary Team, LTS (Tech stack: java/oracle/hadoop/kafka/couchbase/gradle/git/svn) ### Senior Software Engineer @ LinkedIn Jan 2016 – Jan 2018 | Sunnyvale, CA Team Salary. • Lead developer for Salary Search project. Designed and built the backend for the salary search vertical based on LinkedIn Galene framework, including the design of query expansion and ranking algorithms. • Lead developer for company-level insights page. • Optimized bulk data processing speed for LinkedIn Salary backend (latency reduced from over one second to less than 100 milliseconds) ### Software Development Engineer, System @ Yahoo Jan 2014 – Jan 2016 | Sunnyvale, CA • Build Yahoo's centralized audience data pipeline, which delivers user data and analytics of the entire Yahoo user traffic (tech stack: hadoop/pig/hive/oozie) • Maintain and develop large-scale systems that ensure the safety and quality of ads served by Yahoo (tech stack: Java/Spring/Hibernate/MySQL/Oracle/Groovy/C++) • Enabled geo-testing of ads by dynamically routing the network traffic through external proxies (using Apache Traffic Server) • Design and built a creative review server using Netty. • Design and built TNS Offline Service that provides various reporting services and manages scheduled offline jobs. (Jetty/J2EE). ### Software Development Engineer, Interm @ Yahoo Jan 2014 – Jan 2014 • Key member of the Trust and Safety (TnS) team at Yahoo, with responsibilities to maintain and develop systems that ensure the safety and quality of ads served by Yahoo (tech stack: Java/Spring/Hibernate/MySQL/Oracle/Groovy/C++) • Created a performance benchmark driver in Groovy with the following features: ---- Support use of concurrent threads to drive tests ---- Able to collect responses of asynchronous services (JMS-based) ---- Able to drive HTTP-based and JMS-based services. This tool was used to benchmark the majority of applications owned by TnS • Carried out performance benchmark on most TnS applications, and developed analysis tools in Python to analyze the benchmark results. • Was a key member for developing and maintaining the continuous delivery pipeline at Yahoo (tech stack: Java/Groovy/Jenkins) • Architected and implemented a highly scalable, end-to-end test framework for importing open-source Jenkins at Yahoo (tech stack: Java/Groovy/Selenium-WebDriver/PhantomJS/Cucumber). The performance of the framework greatly exceeds the last-generation framework at Yahoo due to its scalability. Key features include: ---- Support multiple browsers (Firefox, PhantomJS) ---- Execute Cucumber scenarios in parallel with customizable process number ---- Able to select what tests to run using annotations. (For example, `gradle test -PtagFilter=smoke+ui` will only run tests annotated with @Smoke AND @Ui). ### Software Engineer @ Progress Financial Jan 2013 – Jan 2014 | Menlo Park, CA • Chief engineer of a risk decision-tree validation harness using TDD methodology in Java/Groovy • Analyzed and improved the performance of a risk engine running on JVM, reducing the running timing by a factor of 4 • Improved the quality of current Java/Groovy code base by refactoring and creating robust tests • Primary architect/developer of the company’s next-generation risk engine using leading enterprise application technologies (EJB/CDI/JPA/JAX-RS/JAXB/Arquillian/Mockito/JUnit) ### Postdoctoral Researcher @ Space Sciences Laboratory, UC Berkeley Jan 2012 – Jan 2013 • Developed software rapidly for NASA Van Allen Probes EFW suite • Developed fast algorithms to solve the problem of hardware response deconvolution for RBSP EFW • Developed solutions to various challenging problems under Java/Eclipse with testing in JUnit • Designed and implemented algorithms to solve the problem of nonlinear spacecraft spin state change due to thermal contraction • Experimented web applications using the Play! Framework with Java/Javascript/MySQL • Developed Python APIs to the NASA CDF C library • Developed efficient programs to compute spacecraft state information from NASA NAIF SPICE kernels. • Developed network programs to transport NASA satellite data. ### Postdoctoral Researcher @ University of Colorado Boulder Jan 2012 – Jan 2012 • Developed a GUI program for manipulating figure-of-merit for a future four-satellite NASA mission. • Developed a GUI program for Tplot, a time series navigation package developed by UC Berkeley. ### Research Assistant @ University of Colorado Boulder Jan 2007 – Jan 2012 • Developed a bibliography management web application in Python/Django • Developed a Mac application in Objective-C/Cocoa to calculate fundamental plasma parameters • Analyzed data from the NASA THEMIS mission, which involves heavy use of digital signal processing, statistical techniques, and numerical analysis. • Developed programs to process large data set and visualize the results. • Developed and maintained data cleaning programs for the THEMIS Electric Field Instrument. • Developed a test-particle particle-in-cell code in Fortran to simulate electron current formation in electron phase-space holes. • Developed automated programs to detect interesting signals using pattern recognition. • Performed hybrid (MPI+OpenMP) parallel code simulations on National Center of Atmospheric Research (NCAR) supercomputers to study kinetic plasma physics. • Performed hybrid simulation to study Kelvin-Helmholtz instabilities in space plasmas. • Developed a hybrid parallel code with MPI/OpenMP in Fortran to reproduce results in Gough et al. (1975, J. Fluid Mech.) with optimization for the NCAR Bluefire supercomputer. • Optimized the design of an energetic particle detector on a CU CubeSat mission in C++ and statistically calculated its signal-to-noise ratio using Geant4 simulation data. ## Education ### Doctor of Philosophy (Ph.D.) in Astrophysical and Planetary Sciences University of Colorado Boulder ### Bachelor of Science (BS) in Earth and Space Sciences University of Science and Technology of China ## Contact & Social - LinkedIn: https://linkedin.com/in/jbtao --- Source: https://flows.cv/jianbao JSON Resume: https://flows.cv/jianbao/resume.json Last updated: 2026-04-12