Sanbao Su

Sanbao Su

Software Engineer

Google

Biography

I am a Software Engineer at Google Cloud, specializing in LLM system infrastructure. I earned my Ph.D. in Computer Engineering from the University of Connecticut. My doctoral research focused on advancing robustness, perception, VLMs, DL, and RL.

I received a bachelor’s degree in automation from Nanjing University, Nanjing, China, in 2016, and a master’s degree in electronic science and technology from Shanghai Jiao Tong University, Shanghai, China, in 2019. After graduation, I worked as a full-time software engineer in Shanghai Huawei Technologies Company, China, from 2019 to 2021. I joined UConn as a Ph.D. student in computer science and engineering starting in Autumn 2021.

News

  • [2025/5] Start my full-time software engineer work in Google Cloud.
  • [2025/5] Defended my Ph.D. dissertation titled “Uncertainty-Aware Algorithms for Robust and Efficient Perception.”. Graduated from the University of Connecticut.
  • [2024/12] Finshed my applied scientist internship at Amazon Robotics, Westborough, MA, USA.
  • [2024/8] Start my applied scientist internship at Amazon Robotics, Westborough, MA, USA.
  • [2024/8] Finished my student researcher internship at Augmented Reality team of Google, Mountain View, CA, USA.
  • [2024/7] Our paper “MetaAT: Active Testing for Label-Efficient Evaluation of Dense Recognition Tasks” is accepted by the 2024 European Conference on Computer Vision (ECCV).
  • [2024/5] Submit one paper to Neurips 2024.
  • [2024/5] Exciting to receive the Pratt & Whitney Advanced Systems Engineering Fellowship and the Predoctoral Fellowship from UCONN.
  • [2023/8] Completed the research internship at Bosch, Sunnyvale, CA, USA. Express my heartfelt gratitude to my manager, mentor and all colleagues.
Interests
  • System Infrastructure
  • Robustness
  • Perception
  • Reinforcement Learning
Education

  • Ph.D. in Computer Engineering, 2025

    University of Connecticut

  • MS in Electronic Science and Technology, 2019

    Shanghai Jiao Tong University

  • BS in Automation, 2016

    Nanjing University

Experience

 
 
 
 
 
Google LLC
Software Engineer
Google LLC
May 2025 – Present Sunnyvale, CA, USA

Responsibilities include:

  • System design
  • Coding
  • Modeling
  • Leading Projects
 
 
 
 
 
University of Connecticut
Research Assistant
University of Connecticut
Sep 2021 – May 2025 Storrs, CT, USA

Responsibilities include:

  • Research
  • Coding
  • Modeling
  • Leading Projects
 
 
 
 
 
Amazon, Amazon Robotics, Scanless Tech Team
Applied Scientist Intern
Amazon, Amazon Robotics, Scanless Tech Team
Aug 2024 – Dec 2024 Westborough, MA, USA

Responsibilities include:

  • Research
  • Data Collection & Annotation
  • Coding
  • Modeling
  • Presentation
 
 
 
 
 
Google, AR Core, Motion Tracking Team
Student Researcher
Google, AR Core, Motion Tracking Team
May 2024 – Aug 2024 Mountain View, CA, USA

Responsibilities include:

  • Research
  • Coding
  • Modeling
  • Demo Presentation
 
 
 
 
 
Bosch Research Center
Research Intern
Bosch Research Center
May 2023 – Aug 2023 Sunnyvale, CA, USA

Responsibilities include:

  • Research
  • Coding
  • Modeling
  • Presentation
  • Submitting paper
 
 
 
 
 
Shanghai Huawei Technologies Company
Full-time Software Engineer
Shanghai Huawei Technologies Company
Apr 2019 – Aug 2021 Shanghai, China

Responsibilities include:

  • Coding
  • Testing
  • Reviewing
  • Collaboration
  • Leading Projects
 
 
 
 
 
UM-SJTU Joint Institute
Research Assistant
UM-SJTU Joint Institute
Sep 2016 – Mar 2019 Shanghai, China

Responsibilities include:

  • Research
  • Coding
  • Modeling
 
 
 
 
 
Cadence Design System Company
Deep Learning Research Intern
Cadence Design System Company
Jul 2018 – Oct 2018 Shanghai, China

Responsibilities include:

  • Designing algorithms
  • Coding
  • Testing

Projects

*
All Deep Learning Other
Multi-Agent Reinforcement Learning for Connected Autonomous Vehicles
Vehicle-to-vehicle (V2V) and Vehicle-to-Infrastructure (V2I) wireless connectivity is the next frontier in road transportation, which will greatly benefit the safety and reliability of autonomous cars. Information shared among autonomous vehicles provides opportunities to better coordination schemes and also raises novel challenges.
Multi-Agent Reinforcement Learning for Connected Autonomous Vehicles
Approximate Logic Synthesis
Recently, much attention has been paid to approximate computing, a novel design paradigm for error-tolerant applications. It can significantly reduce area, power consumption and delay of circuits by introducing an acceptable amount of error.
Approximate Logic Synthesis
Uncertainty Quantification on Collaborative Perception
Multi-agent collaborative perception has been proposed to leverage the viewpoints of other agents to improve the detection accuracy compared with the individual viewpoint. Recent research has shown the effectiveness of early, late, and intermediate fusion of collaborative perception, which respectively transmits raw data, output bounding boxes, and intermediate features, and the improved collaborative perception results will benefit the self-driving decisions of connected and autonomous vehicles (CAVs).
Uncertainty Quantification on Collaborative Perception

Publications

Quickly discover relevant content by filtering publications.
Sanbao Su, Xin Li, Thang Doan, Sima Behpour, Wenbin He, Liang Gou, Fei Miao, Liu Ren (2024). MetaAT: Active Testing for Label-Efficient Evaluation of Dense Recognition Tasks. In ECCV 2024.

Cite Code Project

Sanbao Su, Songyang Han, Yiming Li, Zhili Zhang, Chen Feng, Caiwen Ding, Fei Miao (2024). Collaborative Multi-Object Tracking with Conformal Uncertainty Propagation. In IEEE Robotics and Automation Letters.

PDF Cite Code Project

Songyang Han, Sanbao Su, Sihong He, Shuo Han, Haizhao Yang, Fei Miao (2024). What is the Solution for State-Adversarial Multi-Agent Reinforcement Learning?. In Transactions on Machine Learning Research.

PDF Cite Project

Sihong He, Songyang Han, Sanbao Su, Shuo Han, Shaofeng Zou, Fei Miao (2023). Robust Multi-Agent Reinforcement Learning with State Uncertainty. Transactions on Machine Learning Research.

PDF Cite Code Project

Sanbao Su, Yiming Li, Sihong He, Songyang Han, Chen Feng, Caiwen Ding, Fei Miao (2022). Uncertainty Quantification of Collaborative Detection for Self-Driving. In ICRA 2023.

PDF Cite Code Project

Songyang Han, He Wang, Sanbao Su, Yuanyuan Shi, Fei Miao (2022). Stable and Efficient Shapley Value-Based Reward Reallocation for Multi-Agent Reinforcement Learning of Autonomous Vehicles. In ICRA 2022.

PDF Cite Project

Sanbao Su, Chang Meng, Fan Yang, Xiaolong Shen, Leibin Ni, Wei Wu, Zhihang Wu, Junfeng Zhao, Weikang Qian (2022). VECBEE A Versatile Efficiency-Accuracy Configurable Batch Error Estimation Method for Greedy Approximate Logic Synthesis. In IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

PDF Cite Code Project

Sanbao Su, Chen Zou, Weijiang Kong, Jie Han, Weikang Qian (2020). A Novel Heuristic Search Method for Two-Level Approximate Logic Synthesis. In IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

PDF Cite Project

Sanbao Su, Yi Wu, Weikang Qian (2018). Efficient Batch Statistical Error Estimation for Iterative Multi-level Approximate Logic Synthesis. In DAC 2018.

PDF Cite Project

Contact

  • susanbaonju@gmail.com
  • 1212 Bordeaux Dr, Sunnyvale, CA 94086
  • BORD1212