Sergey Zagoruyko
Senior IOS Developer at Movius
Commerce City, Colorado, United States
Summary
🤩
Rockstar🎓
Top SchoolSergey Zagoruyko is a Senior iOS Developer with 12+ years in IT and over a decade building production iOS apps, specializing in Swift/Objective-C, SwiftUI, MVVM/CLEAN architectures and high-performance real-time communication features. He has led and architected scalable mobile platforms—designing dynamic media feeds, modular SDKs, and VoIP integrations (PJSIP, push-handling, WireGuard) with an emphasis on security (SQLCipher) and reliability. Beyond mobile, Sergey is an active ML and systems open-source contributor with notable work in the Torch/PyTorch ecosystem (including vision models, CUDA backends and attention-transfer research), reflecting deep low-level and research-oriented expertise. That blend of shipping consumer-facing UX and contributing to GPU-accelerated ML tooling gives him a rare cross-domain fluency between mobile engineering and machine learning infrastructure. Based in Commerce City, CO, he pairs practical product delivery with a curiosity for complex systems and performance optimization.
12 years of coding experience
13 years of employment as a software developer
Bachelor of Business Administration (B.B.A.), Business Administration and Management, General, Bachelor of Business Administration (B.B.A.), Business Administration and Management, General at The Open University
English, Russian
Github Skills (61)
pcl10
pytorch10
convolutional-neural-networks10
c-language10
lib10
batch-normalization10
cifar10010
python10
imagenet10
image-classification10
attention-mechanism10
gpu-programming10
torch-hub10
machine-learning10
image-recognition10
Programming languages (9)
Github contributions (5)
szagoruyko/attention-transfer
Jan 2017 - Jul 2018
Improving Convolutional Networks via Attention Transfer (ICLR 2017)
Role in this project:
ML Engineer
ML EngineerContributions:55 commits, 23 PRs, 23 pushes in 1 year 5 months
Contributions summary:Sergey primarily contributed to the training code for various deep learning models within the repository. They added and modified training scripts for CIFAR-10 and ImageNet datasets, showcasing their involvement in model development. The commits demonstrate an understanding of attention transfer techniques, knowledge distillation, and model optimization using PyTorch. These contributions directly align with improving the performance of convolutional neural networks.
pytorchiclrknowledge-distillationdeep-learningconvolutional
szagoruyko/wide-residual-networks
May 2016 - Aug 2019
3.8% and 18.3% on CIFAR-10 and CIFAR-100
Role in this project:ML Engineer
ML EngineerContributions:57 commits, 23 PRs, 28 pushes in 3 years 3 months
Contributions summary:Sergey contributed to the development of various machine learning models within the repository. Their work involved implementing and modifying different neural network architectures, including ResNet, VGG, and NIN, for image recognition tasks. The user also integrated and utilized libraries like Torch and Torchnet within the context of training and evaluating these models. Furthermore, the user updated the training script to work with the Torchnet library.
imagenetcifar-100efficientnetimage-augmentationcifar-10
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.