Zhimin (Jimmy) Zhao is a PhD candidate in SAIL@Queen’s, supervised by Dr. Ahmed E. Hassan (ACM/IEEE Fellow). He received his Master degree from CG@Penn and Bachelor degree from ISC@BIT.

🔎 His research focuses on operations and quality assurance for AI/ML systems (LLMOps, MLOps); applying large language models to automate software engineering tasks (AI4SE, LLM4Code); engineering best practices for AI-powered software (SE4AI).

P.S. My Chinese name is “赵志民” and my English name is “Jimmy Zhao.”

Email: z DOT zhao AT queensu DOT ca

📝 Blogs

  •   Medium’26  The AGI Paradox: We Might Never Realize AGI, and Here is Why

    Zhimin Zhao

    Medium, Jan 2026.

    [blog]

  •   Medium’26  The Vanishing Middle: When Management Becomes the Bottleneck

    Zhimin Zhao

    Medium, Jan 2026.

    [blog]

  •   Medium’26  The Missing Rung: Why CS Graduates Are Facing an Invisible Crisis and What to Do About It

    Zhimin Zhao

    Medium, Feb 2026.

    [blog]

  •   Medium’26  The Oedipus Paradox of Computer Science: Why AI is Slashing the Value of Your Curriculum Before You Even Graduate

    Zhimin Zhao

    Medium, Jan 2026.

    [blog]

  •   Medium’26  When Code Becomes Cheaper Than Debugging: The Rise of Ephemeral Software

    Zhimin Zhao

    Medium, Feb 2026.

    [blog]

📚 Books

  •   Tsinghua’26  零基础AI实战指南:基于阿里云百炼的大模型应用开发 (Zero-to-Hero AI Practical Guide: LLM Application Development on Alibaba Cloud Bailian)

    Ruchun Jia, Zhimin Zhao

    Tsinghua University Press, Under Review, 2026.

    [code]

  •   Tsinghua’25  从DeepSeek到Manus:大模型与多智能体系统原理与实践 (From DeepSeek to Manus: Principles and Practice of Large Models and Multi-Agent Systems)

    Ruchun Jia, Zhimin Zhao

    Tsinghua University Press, Under Review, 2025.

    [code]

  •   Tsinghua’25  生成式人工智能:核心原理与应用 (Generative Artificial Intelligence: Core Principles and Applications)

    Ruchun Jia, Qi Wang, Zhimin Zhao

    Tsinghua University Press, Under Review, 2025.

    [code]

  •   Datawhale’24  钥匙书:机器学习理论导引讲解 (Key Book: A Guide to Machine Learning Theory)

    Zhan Hao, Zhimin Zhao

    Datawhale, 2024.

    [online] [pdf]

📝 Papers

  •   arXiv’26  Why Code, Why Now: Learnability, Computability, and the Real Limits of Machine Learning

    Zhimin Zhao

    arXiv preprint, 2026.

    [paper]

  •   FORGE’25  SE Arena: An Interactive Platform for Evaluating Foundation Models in Software Engineering

    Zhimin Zhao

    ACM International Conference on AI Foundation Models and Software Engineering, 2025.

    [paper] [artifact]

  •   TSE’25  On the Workflows and Smells of Leaderboard Operations (LBOps): An Exploratory Study of Foundation Model Leaderboards

    Zhimin Zhao, Abdul Ali Bangash, Filipe Roseiro Côgo, Bram Adams, Ahmed E. Hassan

    IEEE Transactions on Software Engineering, 2025.

    [paper] [code]

  •   EMSE’25  Investigating Challenges in How FMware is Developed

    Zitao Wang, Zhimin Zhao, Michael W. Godfrey

    Empirical Software Engineering, Under Review, 2025.

  •   EMSE’25  The State of the SBOM Tools Ecosystem and their Prevalence in OSS: A Comparative Analysis of SPDX and CycloneDX

    Abdul Ali Bangash, Tongxu Ge, Zhimin Zhao, Bram Adams

    Empirical Software Engineering, Under Review, 2025.

  •   EMSE’24  An Empirical Study of Challenges in Machine Learning Asset Management

    Zhimin Zhao, Yihao Chen, Abdul Ali Bangash, Bram Adams, Ahmed E. Hassan

    Empirical Software Engineering, 2024.

    [paper] [code]

🔧 Open Source Projects

  • Software Engineering Arena – Initiator. An interactive platform for evaluating foundation models in software engineering through community-driven pairwise comparisons and Elo-based ranking.
  • Easy-Pocket – Initiator. An interactive tutorial for PocketFlow, teaching developers to build chatbots, RAG systems, agents, and workflows using minimal LLM application framework abstractions.
  • Awesome Production Machine Learning – Maintainer. A curated list of open-source libraries for deploying, monitoring, versioning, and securing production ML systems.
  • Auto-Cap – Maintainer. An interactive benchmark dashboard for evaluating cost, accuracy, and performance of sparse Mixture-of-Experts systems.

🎖 Honors and Awards

💬 Service

📖 Educations

📐 Teaching

Queen’s University

University of Pennsylvania

📊 Experience