Zoe Mcclatchey
Senior Tools Engineer at Personal employment
Greater Seattle Area United States
Summary
🤩
Rockstar🎓
Top SchoolZoe Mcclatchey is a Senior Tools Engineer based in the Greater Seattle Area with 14 years of software engineering experience spanning game development, tools, and scientific machine learning. She blends low-level C++ and shader expertise with tooling and tech art for Unreal, having shipped gameplay systems at studios like Undead Labs and Cat Daddy Games and currently building internal toolchains at House of How. A self-taught tinkerer and daily game creator, Zoe maintains parallel personal projects—from RPGs to hybrid city-builder RTS prototypes—that sharpen both her engineering and artistic craft. Her open-source contributions include adaptive loss mechanisms for Physics-Informed Neural Networks in the SciML ecosystem, reflecting a rare cross-domain fluency between game tech and scientific ML. Colleagues rely on her to translate creative design needs into robust, production-ready tools and pipelines that accelerate teams and prototypes alike.
14 years of coding experience
13 years of employment as a software developer
Bachelor of Science (B.S.) Computer Science, Bachelor of Science (B.S.) Computer Science at Wheaton College
English, French, German
Github Skills (13)
neural-network10
partial-differential-equations10
pytorch10
machine-learning10
differential-equations10
fluxor10
tensorflow10
python10
scientific-machine-learning10
flux10
ziggy9
zig9
tensorboard9
Programming languages (7)
Github contributions (5)
SciML/NeuralPDE.jl
Jan 2022 - Mar 2022
Physics-Informed Neural Networks (PINN) Solvers of (Partial) Differential Equations for Scientific Machine Learning (SciML) accelerated simulation
Role in this project:
Back-end Developer & ML Engineer
Back-end Developer & ML EngineerContributions:12 reviews, 33 commits, 9 PRs in 1 month
Contributions summary:Zoe primarily contributed to the `Physics-Informed Neural Networks (PINN) Solvers of (Partial) Differential Equations` project by implementing and modifying adaptive loss mechanisms for the neural network training process. They focused on adding new adaptive loss functions, including GradientNormAdaptiveLoss and MiniMaxAdaptiveLoss, enhancing the flexibility and performance of the solvers. Their work involved modifications to the core `PhysicsInformedNN` structure, particularly around loss weighting and TensorBoard logging integrations, as well as improving testing infrastructure.
simulationscientific-machine-learningpartial-differential-equationsdifferentialode
zoemcc/DFNExperiments.jl
Apr 2022 - Nov 2022
Contributions:91 commits, 83 pushes, 2 branches in 7 months
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.