Zhanhao Liu 💻
Zhanhao Liu

Software Engineer

Google DeepMind

About Me

Zhanhao Liu is a Senior Software Engineer at Google DeepMind, building Gemini Agent. Previously at Google Core Labs, he worked on GenAI Agents, Blockchain, and Identity Management. His expertise spans distributed systems, machine learning, and system design.

Interests
  • GenAI Agent
  • ML System
  • Blockchain
Education

  • MSc in Computer Science

    Georgia Institute of Technology

  • BSc in Computer Science

    Chinese University of Hong Kong

Experience

  1. Senior Software Engineer

    Google DeepMind
    • Building Gemini Agent, an AI assistant that plans and executes complex multi-step tasks through web browsing, deep research, and Google apps integration.

  2. Senior Software Engineer

    Google
    • Core Labs - Researching and building Browser-use AI Agents from scratch to automate web CUJ testing and end-to-end QA workflows.
    • Core Labs - Contributed to the 0-to-1 research, design, and development of a planet-scale blockchain supporting 1M+ TPS, now integrated into Google Cloud’s Universal Ledger.
    • CoreID - Guided a team of 10 engs on building scalable and trusted identity and access management services for Google.

  3. Teaching Assistant & Research Assistant

    Georgia Tech
    • CS 4400 Introduction to Database Systems (Spring/Fall 2019)
    • CS 8803 DML: Data Management and Machine Learning (Fall 2018)
    • Research on Approximate ML via Importance Sampling
    • Research on Automated Feature Engineering: Third Prize in KDD Cup 2019 AutoML Track

  4. Application Engineer Intern

    Google
    • Modeling and prediction of financial time series data via ML

  5. Research Intern

    SenseTime
    • R&D on large-scale ML system

Education

  1. MSc in Computer Science

    Georgia Institute of Technology
    • Grade: 4.0/4.0
    • Specialization: Computing Systems
    • Advisors: Prof. Xu Chu

  2. BSc in Computer Science

    Chinese University of Hong Kong
Project
KDD Cup AutoML Challenge
KDD Cup 2019 ∙ August 2019
3rd prize worldwide in developing AutoML solution for temporal relational data classification with a team of researchers from Alibaba Group and Georgia Tech
FlexPS: Flexible Parallelism Control in Parameter Server Architecture
VLDB 2018 ∙ January 2018
  • Built FlexPS, a Parameter Server system with flexible parallelism control
  • Achieved 400% speedup vs Spark MLlib in k-means++ implementation
  • Optimized sparse data communication, reducing server time by 45%
Publication
Yuzhen Huang, Xiao Yan, Guanxian Jiang, Tatiana Jin, James Cheng, An Xu, Zhanhao Liu, Shuo Tu (2019). Tangram: Bridging Immutable and Mutable Abstractions for Distributed Data Analytics. In USENIX ATC 2019.
PDF Cite Code Video