Curt Park
Machine Learning Engineer at 스노우 SNOW Corporation
South Korea
Summary
🤩
Rockstar🎓
Top SchoolCurt Park is a Machine Learning Engineer with nearly a decade of hands-on experience building production-ready AI systems and backend services from South Korea. He has led teams and initiated projects across industries—shipping text-to-image personalization at SNOW, designing MLOps and high-performance inference at Annotation AI, and applying distributed reinforcement learning for FPGA/ASIC placement at MakinaRocks. Comfortable moving models into production, Curt combines deep learning research (CNN specialization) with system-level skills like Kubernetes migrations, cost optimization, and embedded model compression. An active practitioner in reinforcement learning, his open-source work includes a stepwise DQN-to-Rainbow tutorial that highlights practical RL engineering and reproducible notebooks. Known as a domain-independent problem-solver, he blends product-minded engineering with research curiosity to turn complex algorithms into scalable services.
9 years of coding experience
6 years of employment as a software developer
Bachelor's Degree Computer Science, Bachelor's Degree Computer Science at Dongguk UniversityConvolutional Neural Networks for Visual Recognition, Convolutional Neural Networks for Visual Recognition at Deep Learning College
Korean, English
Stackoverflow
11reputation
903reached
0answers
1question
Github Skills (10)
gymnasium10
pytorch10
dqn10
environ10
python10
reinforcement-learning10
enviroment10
statistics6
deep-learning6
machine-learning6
Programming languages (15)
Github contributions (5)
Curt-Park/rainbow-is-all-you-need
Jun 2019 - May 2022
Rainbow is all you need! A step-by-step tutorial from DQN to Rainbow
Role in this project:
ML Engineer
ML EngineerContributions:12 reviews, 25 commits, 54 PRs in 2 years 11 months
Contributions summary:Curt's contributions primarily involve the development of a Deep Q-Network (DQN) implementation within a Jupyter Notebook environment, as suggested by the "01.dqn.ipynb" file. They added code related to a ReplayBuffer for experience replay and a DQN agent capable of action selection. Furthermore, the user integrated a testing functionality, along with the utilization of PyTorch for model definition and training within a reinforcement learning context.
pytorchreinforcement-learningrainbowgym-environmentneed
Curt-Park/style_transfer_keras
Feb 2018 - Mar 2018
Contributions:20 commits, 56 pushes, 5 branches in 9 days
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.