Anh Truong
Staff Machine Learning Engineer at Tubi
Urbana, Illinois, United States
Summary
🤩
Rockstar🎓
Top SchoolAnh Truong is a machine learning engineer with 11 years of experience specializing in AI, recommendation systems, NLP, and synthetic data generation, currently based in Urbana, Illinois. She has driven production-grade deep learning and content-ranking solutions at Tubi, improving homepage personalization, inference efficiency, and multi-framework workflows for movie recommendations. At Capital One she built sensitive information detection pipelines, automated ML tooling, and contributed performance and robustness fixes to the open-source DataProfiler project, improving CSV parsing and data labeling. Her PhD work on online recommendation and sleeping experts adds a strong theoretical grounding to her applied work in sequential models and bandits. Known for pragmatic optimization—memory and latency-conscious model and pipeline improvements—she bridges research and engineering to deliver scalable solutions. Outside product work she has applied generative models and business rules to create realistic synthetic datasets for testing and privacy-aware use cases.
11 years of coding experience
5 years of employment as a software developer
Bachelor's Degree Telecommunications Engineering, Bachelor's Degree Telecommunications Engineering at HoChiMinh city University of TechnologyDoctor of Philosophy (Ph.D.) Industrial Engineering, Doctor of Philosophy (Ph.D.) Industrial Engineering at University of Illinois Urbana-Champaign
English, French, Vietnamese
Github Skills (9)
data-labeling10
pandas10
csv10
python10
data-science10
data-profiling10
data-analysis10
testing9
machine-learning9
Programming languages (1)
Github contributions (5)
capitalone/DataProfiler
Feb 2021 - Aug 2021
What's in your data? Extract schema, statistics and entities from datasets
Role in this project:
Data Scientist
Data ScientistContributions:596 reviews, 35 commits, 58 PRs in 6 months
Contributions summary:Anh focused on improving the performance and functionality of the data labeling process within the dataprofiler repository. They optimized memory usage during string conversions in the data labeler. Furthermore, the user addressed and fixed a delimiter issue in the CSV data reader, adding test coverage to prevent incorrect data parsing. They also made improvements to the header detection and incorporated additional test files to enhance the robustness of the data profiling process. Finally they worked on the data labeler examples, providing more test cases and code refactoring.
csvpythondatanpistatistics
AnhTruong/DataProfiler
Mar 2021 - Aug 2021
What's in your data? Extract schema, statistics and entities from datasets
Contributions:28 PRs, 251 pushes, 11 branches in 5 months
statisticspythondatadata-sciencedataset
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.