Edwin Ng
Senior Applied Scientist at Amazon
San Francisco, California, United States
Summary
🤩
Rockstar🎓
Top SchoolEdwin Ng is a Senior Applied Scientist based in San Francisco with seven years of industry experience building scalable forecasting, causal inference, and decision-science solutions at companies like Amazon and Uber. He blends a strong quantitative foundation—M.S. degrees in Statistics and Financial Engineering from UCLA—with hands-on engineering, shipping probabilistic and Bayesian forecasting work (including contributions to the well-known uber/orbit forecasting repo and Pyro-based notebooks). At Uber he progressed from individual contributor to Manager II, driving budget optimization, planning, and actionable forecasting products; at Amazon he continues to apply those skills to production science problems. His background spans finance, trading, and analytics roles, giving him a rare mix of domain knowledge and production ML expertise. Colleagues describe him as a pragmatic scientist who translates complex probabilistic models into operational decisions. He maintains a personal site (edwinng.com) that showcases his technical work and experiments.
7 years of coding experience
10 years of employment as a software developer
M.S. Financial Engineering, M.S. Financial Engineering at UCLA Anderson School of ManagementCulture | Leadership, Culture | Leadership at Harvard Business School Executive EducationUniversity of California, Los Angeles
Chinese, English
Github Skills (10)
bayesian-statistics10
forecasting10
forecast10
time-series10
bayesian10
probabilistic-programming10
python10
machine-learning9
stan8
regression-models8
Programming languages (5)
Github contributions (5)
uber/orbit
May 2020 - Jan 2023
A Python package for Bayesian forecasting with object-oriented design and probabilistic models under the hood.
Role in this project:
Data Scientist
Data ScientistContributions:37 releases, 200 reviews, 87 commits in 2 years 9 months
Contributions summary:Edwin's commits primarily involve reverting changes within the `examples/LGT_Pyro_Example.ipynb` notebook. These changes appear related to experiments with Bayesian forecasting models, specifically involving the Pyro library for probabilistic programming and a model related to "LGT". The user is also making changes to the example notebook, and there is an associated notebook demonstrating a full bayesian approach for modeling.
forecastingpythonregression-modelstimeseries-forecastingforecast
edwinnglabs/karpiu
Jun 2022 - Mar 2023
Karpiu is a package designed for marketing mix modeling by calling Orbit from the backend. Karpiu is still in its beta version. Please use it at your own risk.
Contributions:3 releases, 1 review, 198 commits in 9 months
callingpythonriskmarketing-analyticsorbit
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.