Skip to content
View Shawn-Dong's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report Shawn-Dong

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.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

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

Report abuse
Shawn-Dong/README.md

Hi, I'm Shawn Dong

Backend · Distributed Systems · AI Agent Platforms

I build the backend that agent products run on — task stores, dispatch, and data pipelines.

M.S. Artificial Intelligence @ Columbia '28 · B.S.E. Computer Engineering @ Michigan '26
SWE Intern @ NevaMind AI

📄 Resume · LinkedIn


Open Source

159 merged PRs in total — most of them in private agent-platform repos at NevaMind.


Projects

  • creekstone-lark-kit · Python — propose → approve → apply changeset engine that puts agent writes behind an approval gate, with an append-only audit log
  • KSS Rating Platform · PostgreSQL · Docker · S3 — multi-scorer annotation platform for drowsiness research, built for 20 researchers and 50k+ annotations
  • PET-Based Lymphoma Classification · PyTorch — feature fusion across four medical foundation models over CT and PET

Tech Stack

Languages Go Python TypeScript SQL

Backend FastAPI Django gRPC Kafka Redis

Data PostgreSQL MongoDB

Ops Docker AWS GitHub Actions Grafana

Pinned Loading

  1. PET-Based-Hodgkin-s-Lymphoma-Classification-via-Foundation-Model-Feature-Fusion PET-Based-Hodgkin-s-Lymphoma-Classification-via-Foundation-Model-Feature-Fusion Public

    Hodgkin's lymphoma classification from PET/CT by fusing embeddings from four medical foundation models

    Jupyter Notebook 1 1

  2. creekstone-lark-kit creekstone-lark-kit Public

    Approval-gated changeset engine for agent writes to Lark — propose → approve → apply, with an append-only audit log

    Python

  3. Rating_platform Rating_platform Public

    Multi-scorer image annotation platform for drowsiness research (Karolinska Sleepiness Scale) — PostgreSQL, S3, Dockerized deployment

    JavaScript

  4. NevaMind-AI/memU NevaMind-AI/memU Public

    Personal memory across agents

    Python 14.4k 1.1k