Hi, my name is Chan Kha Vu. I’m a ML engineer at Microsoft in Seattle Area, currently working on image ranking models at Bing. Every time you search for images on Bing, the final results page are formed by the models trained with my code!

Previously, I worked at Samsung Research on Monocular 3D Reconstruction, Multi-Task Learning, and optimizing Conv Nets for resource-constrained mobile devices. On a side for fun, I read (a lot of) Manga, play Go (feel free to send me a challenge), and a bit of Kaggling (let’s team up). I’m from Ukraine, by the way!

My journey

2021 — Now: ML Engineer @ Microsoft, Seattle, USA
Developing web-scale image/video search relevance ranking models at Bing. I feel incredibly fortunate to work with amazing people who are much smarter than me!
2019 — 2021: SWE @ Microsoft, Seattle, USA
Developed accessibility features for Excel (worked both on server-side and client-side) and deployed globally for millions of users. Feels good to make life easier for people!
2017 — 2019: ML Engineer @ Samsung Research, Ukraine
Monocular 3D Reconstruction, Multi-Task Learning, and On-Device AI. Trained SOTA multi-task models that was 50x smaller than previous SOTA on each individual task.
2017 — 2019: Taras Shevchenko National University of Kyiv
Master’s degree in Applied Mathematics. Thesis: “Adaptive representation sharing in Multi-Task Networks” — created a novel NAS algorithm for Multi-Task ConvNets.
2013 — 2017: Taras Shevchenko National University of Kyiv
Bachelor of Science in Applied Mathematics. Thesis: “Breast Cancer Screening by analyzing the Interphase Nuclei of the Buccal Epithelium.”

Kaggle

I’m a Competition Master on Kaggle — a platform for Machine Learning challenges. Some of the competitions that I really enjoyed:

Talks & teaching

  • Talk at Samsung Research: “Multi-Objective Optimization and Multi-Task Learning”
    SRK AI Conference 2019, Samsung Research, Ukraine (with an audience of 150+ attendees).

  • Lecture at Kyiv DS Community: “Deep Metric Learning” (video)
    Kyiv Data Science Community, as part of the “Introduction to ML and Neural Nets” course, 2021.

  • Talk at Summer IT Camp at KNU: “Using LLMs: promting, agents, tuning” (slides)
    Summer IT Camp, Taras Shevchenko National University of Kyiv, 2023.

  • Teaching Assistant: “Pattern Recognition” course for Master’s students.
    Taras Shevchenko University, Fall 2019. Used d3.js to make this cool visualization of HOG!