Andy Kim
Software Engineer II at Microsoft
Vancouver, British Columbia, Canada
Summary
👤
Senior🎓
Top SchoolAndy Kim is a Software Engineer II with eight years of experience building user-facing and systems-level features at Microsoft and Unity, grounded in a Computer Science degree from UBC. He has shipped accessibility, security, and performance improvements for Microsoft Photos and now integrates LLM-driven experiences into PowerPoint Designer. His background spans C++/WinRT and C# desktop engineering, animation tooling, and VFX pipeline tooling, giving him a rare blend of product-focused UI work and low-level platform maintenance. An active open-source contributor, he improved training robustness and model persistence for the popular deepfakes faceswap project, reflecting practical ML engineering chops alongside production software delivery. Based in Vancouver, he also mentors new engineers and balances feature development with operational compliance and security coordination.
8 years of coding experience
5 years of employment as a software developer
Bachelor of Science - BS Computer Science, Bachelor of Science - BS Computer Science at The University of British Columbia
Github Skills (6)
neural-network10
machine-learning10
deep-learning10
python10
pytorch6
pytorch-lightning6
Programming languages (7)
Github contributions (5)
deepfakes/faceswap
Apr 2018 - Apr 2018
Deepfakes Software For All
Role in this project:
ML Engineer
ML EngineerContributions:6 commits, 1 PR, 11 comments in 1 day
Contributions summary:Andy primarily focused on modifying the training process within the `faceswap` project. Their commits involve changes to the `train.py` script, including adding functionality to save the model at specific epochs and controlling the training flow upon abrupt stops. These modifications suggest an effort to refine the training procedure for deepfake models and improve model persistence during the training phase.
deepfakesdeep-learningneural-netsmachine-learningface-swap
andykdy/N-Queens
Feb 2020 - Jun 2020
Solving N-Queens with genetic algorithm
Contributions:16 PRs, 30 pushes, 5 branches in 4 months
pythonsolvinggeneticn-queensqueens
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.