Kuang Lu
Research Scientist at Facebook
Seattle, Washington, United States
Summary
🤩
Rockstar🎓
Top SchoolKuang Lu is a research scientist at Facebook in Seattle with a decade of experience at the intersection of information retrieval and applied machine learning. He holds a PhD in Computer Engineering from the University of Delaware and has a strong academic track record researching query performance prediction to choose optimal retrieval models. At Facebook he has worked on both research and ML-focused engineering problems, previously building domain-level signals to demote low-quality web content in production. Kuang is an active open-source contributor to Anserini, the widely used Lucene-based IR toolkit, where he enhanced fine-tuning, cross-validation, relevance feedback, and collection-handling scripts to improve reproducibility and performance. He combines rigorous experimental methods from academia with pragmatic engineering for scalable systems, and often focuses on the less-visible but high-impact plumbing—data handling, evaluation pipelines, and model selection—that makes IR research production-ready.
10 years of coding experience
5 years of employment as a software developer
Doctor of Philosophy - PhD, Computer Engineering, Doctor of Philosophy - PhD, Computer Engineering at University of Delaware
Github Skills (9)
lucene10
information-retrieval10
python10
api8
apidoc8
java7
javas7
testing6
machine-learning5
Programming languages (4)
Github contributions (5)
castorini/anserini
Oct 2018 - Jul 2020
Anserini is a Lucene toolkit for reproducible information retrieval research
Role in this project:
Back-end Developer
Back-end DeveloperContributions:6 reviews, 10 commits, 20 PRs in 1 year 9 months
Contributions summary:Kuang primarily contributed to the fine-tuning and evaluation processes within the Anserini project. Their work included adding and modifying scripts for cross-validation, parameter tuning, and result reporting, specifically focusing on fine-tuned results. They also added new functionalities for relevance feedback and made modifications to the core classes that affect how the system handles data and interacts with collections. Furthermore, the user expanded the query generation scripts and collection data handling, focusing on optimizing performance and output.
reproducibleretrievalluceneinformation-retrievaljava
lukuang/Anserini
Oct 2018 - Jul 2020
An information retrieval toolkit built on Lucene
Contributions:38 pushes, 21 branches in 1 year 9 months
solrsynonymsretrievalluceneinformation-retrieval
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.