Cuong Duong
Senior Machine Learning Engineer at Anduril Industries
Sydney, New South Wales, Australia
Summary
🤩
Rockstar🎓
Top SchoolCuong Duong is a Senior Machine Learning Engineer in Sydney with 8 years’ experience turning user interaction data into actionable product decisions, most recently at Anduril and formerly leading ML and analytics initiatives across Canva. He combines rigorous statistical inference and experiment design with practical engineering—setting up core analytics pipelines, auto-labeling workflows using Vision LLMs, and shipping real-time classification and click-based ranking that measurably improved engagement. A former consulting actuary and FIAA fellow, he brings deep experience in long-horizon risk modelling and causal measurement to product strategy and growth trade-offs. Cuong is also an active open-source contributor (notably to Facebook Prophet), reflecting his taste for robust, production-ready tooling across Python/R/SQL.
8 years of coding experience
6 years of employment as a software developer
Fellowship Actuarial Science, Fellowship Actuarial Science at Actuaries InstituteActuarial Science, Actuarial Science at Macquarie UniversityThe University of MelbourneVictorian Certificate of Education, Victorian Certificate of Education at Melbourne High School
Github Skills (6)
forecasting10
forecast10
statistical-models10
python10
r10
machine-learning9
Programming languages (5)
Github contributions (5)
facebook/prophet
Aug 2020 - Jan 2023
Tool for producing high quality forecasts for time series data that has multiple seasonality with linear or non-linear growth.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:11 releases, 90 reviews, 55 commits in 2 years 5 months
Contributions summary:Cuong primarily contributed to the development of a helper function to summarize the coefficients of extra regressors, which is a core utility function for the project. Their work involved implementing the function in Python and R, adding tests for the utility, and generating documentation. Furthermore, the user upgraded the CmdStanPy interface. The user also added a 'flat' growth option in the docstring of the python code, demonstrating an understanding of the project's modeling and forecasting capabilities.
forecastingpythontime-series-analysisforecasting-modelsforecasts
tcuongd/prophet
May 2021 - Sep 2022
Tool for producing high quality forecasts for time series data that has multiple seasonality with linear or non-linear growth.
Contributions:2 releases, 26 pushes, 10 branches in 1 year 4 months
forecastingtime-series-analysisforecastslinearnon-linear
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.