Elena Ehrlich
Principal Data Science Manager
United States
Summary
🤩
Rockstar🎓
Top SchoolElena Ehrlich is a Principal Data Science Manager at AWS with 10+ years of experience building ML-driven products that deliver rapid go-to-market value across sports analytics, esports, finance, defense, and advertising. Trained as a statistician (PhD, Imperial College London), she specializes in adaptive, real-time algorithms for partially observed, non-linear systems and has a track record of turning complex sequential inference problems into production-grade solutions. Her work spans demand forecasting and price optimization to target tracking and correlated-asset modeling, and she’s led AI/ML professional services and MVP delivery for enterprise customers at scale. An active contributor to probabilistic time-series tooling, she extended GluonTS with a Generalized Pareto distribution implementation, blending deep research roots with pragmatic open-source impact. Known for marrying rigorous statistical methods with product-focused engineering, she thrives on solving latency-sensitive problems where incoming-data frequency dictates design.
10 years of coding experience
7 years of employment as a software developer
Doctor of Philosophy (Ph.D.) Statistics, Doctor of Philosophy (Ph.D.) Statistics at Imperial College London
Github Skills (15)
data-modeling10
forecasting10
machine-learning10
pytorch10
time-series10
forecast10
probabilistic-programming10
statistical-models10
python10
probabilistic-reasoning10
probabilistic-models10
mxnet9
deep-learning8
deeplearning-ai8
unit-testing8
Programming languages (1)
Github contributions (5)
awslabs/gluonts
Sep 2020 - Aug 2022
Probabilistic time series modeling in Python
Role in this project:
Data Scientist
Data ScientistContributions:4 reviews, 7 commits, 15 PRs in 1 year 11 months
Contributions summary:Elena contributed to the implementation and testing of the Generalized Pareto distribution within the GluonTS library, specifically focusing on its integration for probabilistic time series modeling. They added the `GenPareto` distribution class, related methods (cdf, quantile), and integrated it into existing test frameworks. Furthermore, the user addressed issues by modifying the existing code base. This demonstrates a focus on expanding the library's capabilities for time series analysis and probability distributions.
forecastingpythontime-series-analysistimeseries-forecastingaws
elenaehrlich/gluon-ts
Sep 2020 - Aug 2022
Probabilistic time series modeling in Python
Contributions:25 pushes, 3 branches in 2 years
pythontime-series-analysismachine-learningprobabilistictime-series
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.