Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings
@kozistr
kozistr
Follow
View kozistr's full-sized avatar
🏝️
rest

Hyeongchan Kim kozistr

🏝️
rest

Organizations

@Data-Competition

Block or report kozistr

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
kozistr /README.md

hey there


Hello! I'm Hyeongchan from Korea. I enjoy programming, working out, and bouldering.

  • Service many machine learning products in various domains, Audio & Speech, Vision, NLP, Recommendation Systems, Tabular, and LLM applications in many startups.
  • Kaggle 2x Expert. the highest competition rank is top 0.1%.
  • Here's my C.V. Feel free to contact me at the email kozistr@gmail.com :)

previously...

  • 2023 - 2024 : Joined Sionic.AI. Built enterprise-grade LLM applications.
  • 2021 - 2023 : Joined Viva Republica (Toss). Developed many products like BNPL, CSS, OCR, NPS, CDP, and in-house products.
  • 2020 - 2021 : Joined Watcha. Developed Watcha recommendation system, and contributed to other products like WatchaPedia, in-house applications.
  • 2019 - 2020 : Joined Rainist (Banksalad). Developed a transaction classifier service to analyze the categories with low latency, high accuracy, and in real-time.
  • 2019 : Joined VoyagerX. Developed a speaker diarization product that automatically recognizes the contents of the meeting.
  • - 2019 : offensive security stuffs. Mainly researched and studied Linux kernel exploitation and reverse engineering.

Current Interests

  • Kaggle Challenges
  • Building something in Rust
  • Bouldering

πŸ“Š this week i spent my time on:

Profile Views

Lines of code

I'm a Night πŸ¦‰

🌞 Morning 967 commits β–ˆβ–ˆβ–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘ 06.40 % 
πŸŒ† Daytime 6053 commits β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘ 40.08 % 
πŸŒƒ Evening 5530 commits β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘ 36.62 % 
πŸŒ™ Night 2552 commits β–ˆβ–ˆβ–ˆβ–ˆβ–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘β–‘ 16.90 % 

Last Updated on 11/02/2026 15:57:12 UTC

πŸ“ˆ my github stats

kozistr

Pinned Loading

  1. pytorch_optimizer pytorch_optimizer Public

    optimizer & lr scheduler & loss function collections in PyTorch

    Python 388 36

  2. Awesome-GANs Awesome-GANs Public

    Awesome Generative Adversarial Networks with tensorflow

    Python 763 165

  3. rcan-tensorflow rcan-tensorflow Public

    Image Super-Resolution Using Very Deep Residual Channel Attention Networks Implementation in Tensorflow

    Python 54 21

  4. Awesome-Segmentations Awesome-Segmentations Public

    Lots of semantic image segmentation implementations in Tensorflow/Keras

    Python 62 15

  5. AdaBound-tensorflow AdaBound-tensorflow Public

    An optimizer that trains as fast as Adam and as good as SGD in Tensorflow

    Python 46 6

  6. kozistr.github.io kozistr.github.io Public

    my github blog

    TypeScript 4

AltStyle γ«γ‚ˆγ£γ¦ε€‰ζ›γ•γ‚ŒγŸγƒšγƒΌγ‚Έ (->γ‚ͺγƒͺγ‚ΈγƒŠγƒ«) /