CV

A copy of my CV can be downloaded here.
This file was last updated on Thu Dec 18 2025.

Bio

Designing Multi-Agent Systems Book Cover
Learn More →
I wrote a book on AI agents!
I am an experienced technical leader and Principal Research Software Engineer at Microsoft Core AI, where I build AI agent infrastructure and developer tools (core developer for AutoGen, Microsoft Agent Framework and contributor at Azure Foundry). My research interests span AI agents, developer tools, and human-AI interaction. My research has been published at conferences such as ACL, EMNLP, AAAI, and CHI and has received multiple best paper awards. My work has also been featured in outlets such as the Wall Street Journal, VentureBeat, CIO
here
. I am an IEEE Senior member, a Google Certified Professional ( Data Engineer, Cloud Architect ) and currently a Google Developer Expert in Machine Learning.
I hold a PhD in Information Systems from City University of Hong Kong (recipient of the HKPFS scholar award by the Hong Kong Research Grants Council). My dissertation studied developer contribution behaviour in software crowdsourcing contests - factors influencing participation, the impact of incentives on participation behaviour and the problem solving process within crowdsourcing contests. Prior to City University, I studied at the Information Networking Institute at Carnegie Mellon University where I earned a Masters degree in Information Networking. I previously worked as a Principal Research Engineer at Cloudera Fast Forward Labs, Research Staff Member at IBM Research, Technical Lead for MIT Global Startup Labs, Researcher at the Innovation Management Lab, Athens Information Technology Athens Greece, and founder/lead developer for a small startup focused on West African markets.
In my free time, I enjoy music (some self taught guitar, piano), sports (participated in the Hong Kong Marathon thrice) and exploring art (some drawing, 3d modelling, african mask art).
All content on this site are my ideas and do not reflect opinions of my employer.

Experience

Microsoft Core AISanta Clara, California
May 2025 – Present
Principal Research Software Engineer (AI Agents)
  • Core contributor for Microsoft Agent Framework (5.9K GitHub stars). Built DevUI (470K+ downloads), the primary testing and debugging interface.
  • Advised UI direction across 3 product surfaces: Agent Framework OSS, VSCode Extension, Azure Foundry. Design patterns influenced Microsoft Foundry workflow UI.
  • DRI for internal MCP standards. Work featured at Microsoft Build and Ignite 2025.
Microsoft Research – AI Frontiers LabSunnyvale, California
October 2021 – May 2025
Principal Research Software Engineer (Generative AI)
  • Core developer for AutoGen (52K+ GitHub stars, 5.9M+ downloads). Shepherded merger with Semantic Kernel into Microsoft Agent Framework. Co-authored Magentic-One, a reference architecture for autonomous multi-agent systems.
  • Created LIDA (3.2K GitHub stars), an automated visualization framework using LLMs. Approaches adopted by Excel, Fabric, PowerBI teams.
  • Proposed and implemented evaluation metrics used to select candidate GitHub Copilot models for production.
Cloudera Fast Forward LabsNew York City / Palo Alto
January 2019 – September 2021
Principal Research Engineer (Machine Learning)
  • Led research reports on Deep Learning for Question Answering, Anomaly Detection, and Image Analysis.
  • Led development of Applied ML Prototypes (AMPs) for Cloudera Machine Learning, the standard tool for customer onboarding and demonstrations.
IBM ResearchYorktown Heights, New York
April 2016 – January 2019
Research Staff Member
  • Created Data2Vis, the first neural network approach to automatic data visualization (IEEE CG&A Best Paper 2019, IEEE VIS Best Paper Honorable Mention 2018).
  • Co-created TJBot, an open-source DIY AI kit adopted by 8,000+ users for classroom teaching and corporate training.

Education

City University of Hong KongKowloon Tong, Hong Kong
2012 – 2016
PhD in Information Systems (Quantitative User Behaviour, HCI)
Recipient of the HKPFS scholar award by the Hong Kong Research Grants Council.
Carnegie Mellon UniversityPittsburgh, USA
2009 – 2011
MSc Information Networking

Key Projects

AutoGen
Agent Framework
AutoGen Studio
LIDA

Book

Designing Multi-Agent Systems — Amazon Best Seller, #1 New Release in AI category. A 398-page practical guide on AI agent design, building, and evaluation.

Awards

  • [2020] Best Paper Award, IEEE Computer Graphics & Applications (Data2Vis).
  • [2018] Best Paper Honorable Mention, IEEE VIS Symposium on Visualization in Data Science.
  • [2018] Best Technical Demonstration, AAAI Conference on Artificial Intelligence.
  • [2018] Heidelberg Laureate Forum (1 of 200 young researchers invited).
  • [2019] Grand Prize Winner, #BuiltWithTensorflow challenge (Handtrack.js).
  • [2018] Invited speaker, TensorFlow Summit (2018, 2019).
  • [2017] IBM Open Source Award.

Patents

Granted Patents
  • Saleema Amershi, Adam Fourney, Victor Dibia, Gagan Bansal (2025). Embedded Attributes for Modifying Behaviors of Generative AI Systems. US Patent 12,423,338.
  • Victor Dibia (2026). Automated generation of data visualizations and infographics using large language models and diffusion models. US Patent 12,518,447.
  • Victor Dibia, Adam Fourney, Forough Poursabzi-Sangdeh, Saleema Amershi (2025). Coding activity task (CAT) evaluation for source code generators. US Patent 12,254,293.
  • Victor Dibia (2021). Detecting Human Input Activity In a Cognitive Environment Using Wearable Inertia and Audio Sensors. US Patent 11,195,118.
  • Victor Dibia, Rachel K.E. Bellamy (2019). Automated Summarization Based on Physiological Data. US Patent 10,353,996.
  • Victor Dibia, Rachel K.E. Bellamy (2018). Using Ultraviolet Sensor Data to Determine a Pseudo Location of a User. US Patent 10,066,987.
-> All Publications

Talks

A list of talks I have delivered.
  • June 2025

    AI.Engineer ConferenceSF, Marriott Marquis.

    UX Design Principles for Semi-Autonomous Multiagent Systems
    slides blog post
  • November 2024

    QCon San Francisco 2024San Francisco, USA.

    10 Reasons Your Multi-Agent Workflows Fail and What You Can Do About It
    Talk Page slides
  • October 2024

    CfD Conversations SeriesHybrid (In-person & Virtual).

    What Can GenAI Really Do for Data Visualization?
    event
  • December 2023

    Ai.dev / Cassandra SummitSan Jose, McEnery Convention Center.

    AutoGen: NextGen AI Applications via Multi Agent Conversations
    recording
  • June 2021

    Fast Forward LiveOnline.

    Deep Learning for Automatic Offline Signature Verification
    recording
  • November 2019

    QCON SFSan Francisco, USA.

    ML in the Browser: Interactive Experiences with Tensorflow.js
    recording
  • November 2019

    Tensorflow World Santa Clara, California USA.

    Handtrack.js: Building gesture-based interactions in the browser using TensorFlow.js
  • November 2019

    Google ML SummitPittsburgh PA, Cambridge, USA.

    Art + AI : Generating Novel African Mask Art using Generative Adversarial Networks
    recording
  • September 2019

    OReilly Strata Data Conference New York, USA.

    Handtrack.js: Building gesture-based interactions in the browser using TensorFlow
  • May 2019

    !!Con New York, USA.

    Dance of the Ancestors: I used Neural Networks to Re-imagine African Mask Art !!
    recording
  • March 2019

    NVIDIA GTC San Jose, California, USA.

    Data2Vis: Automatic Generation of Data Visualizations Using Sequence-to-Sequence Recurrent Neural Networks.
    recording slides

Read the Newsletter.

Read and Subscribe
Powered by Substack. Privacy Policy.

I write a monthly newsletter on Applied AI and HCI. Subscribe to get notified on new posts.

Feel free to reach out! Twitter, GitHub, LinkedIn

.