Jaewon Chung
PhD Researcher - NeuroData Laboratory
Baltimore, Maryland, United States
Summary
👤
Senior🎓
Top SchoolJaewon Chung is a computational neurodata scientist and postdoctoral fellow with a decade of experience building reproducible, scalable pipelines for large neuroimaging and EM datasets. Trained as a PhD in Biomedical Engineering at Johns Hopkins, he develops statistical and causal machine-learning methods for population-level connectome analysis and maintains the graph statistics library graspologic in collaboration with Microsoft Research. His open-source contributions include performance and robustness improvements to DIPY’s Gibbs denoising and making graspologic more sklearn-compliant, reflecting a focus on production-quality research software. Jaewon blends cloud-scale data engineering (AWS Batch/S3) with algorithmic work in Python, PyTorch, and Numba, and has a track record applying these tools across neuroscience and protein modeling domains. Notably, he pairs rigorous method development with practical tooling—such as online annotation interfaces and CI-backed libraries—so others can reproduce and extend his work.
10 years of coding experience
Doctor of Philosophy - PhD, Biomedical Engineering, Doctor of Philosophy - PhD, Biomedical Engineering at The Johns Hopkins University School of MedicineBachelor of Arts (B.A.), Neurobiology and Behavior, Economics, Bachelor of Arts (B.A.), Neurobiology and Behavior, Economics at Wesleyan UniversityJohns Hopkins University
Korean, English
Github Skills (17)
test-automation10
python10
testing10
numpy10
denoising10
medical-imaging10
data-science9
scipy9
python-multiprocessing9
machine-learning9
graph-theory9
multi-process9
multiprocessing9
data-structures8
data-structure8
Programming languages (10)
Github contributions (5)
graspologic-org/graspologic
Sep 2018 - Dec 2022
Python package for graph statistics
Role in this project:
Back-end Developer
Back-end DeveloperContributions:6 releases, 56 reviews, 222 commits in 4 years 3 months
Contributions summary:Jaewon made several contributions related to the package's underlying code structure, addressing setup and testing. They made the implementation of the library classes more sklearn-compliant by renaming variables and function names. The changes also improved the overall code style.
statisticspythondata-sciencenetworksgraph-statistics
dipy/dipy
Sep 2020 - Oct 2020
DIPY is the paragon 3D/4D+ medical imaging library in Python. Contains generic methods for spatial normalization, signal processing, machine learning, statistical analysis and visualization of medical images. Additionally, it contains specialized methods for computational anatomy including diffusion, perfusion and structural imaging.
Role in this project:Backend Developer & Test Automation Engineer
Backend Developer & Test Automation EngineerContributions:2 reviews, 15 commits, 2 PRs in 11 days
Contributions summary:Jaewon's primary focus was on enhancing the `dipy` library's Gibbs ringing functionality. They implemented an `inplace` keyword argument and added comprehensive tests to validate its behavior across different data dimensions. Further improvements included parallelization of the Gibbs denoising algorithm using multiprocessing, and the addition of type checking and error handling. These contributions significantly improved the usability, robustness, and performance of the Gibbs ringing feature.
signalpythonmicrostructurespatialtractography
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.