Yan Wu
Software Engineer at ByteDance
Seattle, Washington, United States
Summary
🤩
Rockstar🎓
Top SchoolYan Wu is a software engineer in Seattle with 11 years of experience building full-stack and data-driven systems, currently working on monetization and ad growth at ByteDance after prior roles at AWS. He brings strong Java expertise and a broad polyglot backend skill set (Python, C, Swift/Objective-C) alongside front-end experience in JavaScript, HTML/CSS and enterprise frameworks like Spring and Hibernate. Yan has hands-on big data experience with Hadoop ecosystem tools (MapReduce, Hive, HBase, Mahout) and both MongoDB and Cassandra, enabling him to bridge analytics and production services. He contributes to open-source ML tooling—most recently improving core diffusion model code and conditional adapter sampling in the popular T2I-Adapter project—highlighting an interest in generative models. Comfortable operating in cloud environments (AWS) and developer tooling (Git/GitHub), he combines product-focused engineering with a curiosity for new technologies. Colleagues would note his pragmatic approach to shipping scalable systems and his habit of learning by contributing to open-source research code.
11 years of coding experience
3 years of employment as a software developer
Master's Degree, Information Systems, Master's Degree, Information Systems at Northeastern UniversityBachelor of Business Administration (B.B.A.), Management Information Systems, General, Bachelor of Business Administration (B.B.A.), Management Information Systems, General at Harbin Institute of Technology
English, Chinese
Github Skills (5)
diffusion-models10
computer-vision10
pytorch10
machine-learning10
deep-learning10
Programming languages (3)
Github contributions (5)
TencentARC/T2I-Adapter
Feb 2023 - Mar 2023
T2I-Adapter
Role in this project:
ML Engineer
ML EngineerContributions:54 commits, 1 PR, 19 pushes in 26 days
Contributions summary:Yan primarily contributed to the `ldm/models/diffusion/ddpm.py`, `ldm/models/diffusion/ddim.py`, and `ldm/models/diffusion/plms.py` files, indicating a focus on the core diffusion model architecture. Their commits include updates to parameterization methods, and modifications to sampling and loss calculations. Furthermore, the user has incorporated changes related to conditional sampling using adapters within the `test_keypose.py`, `test_sketch.py`, `test_sketch_edit.py`, and `test_composable_adapters.py` files.
ToTheBeginning/PuLID
Apr 2024 - Jul 2025
[NeurIPS 2024] Official code for PuLID: Pure and Lightning ID Customization via Contrastive Alignment
Contributions:2 PRs, 31 pushes, 75 comments in 1 year 3 months
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.