Julien Herzen
Sr Engineering Manager at Isomorphic Labs
Lausanne, Vaud, Switzerland
Summary
🤩
Rockstar🎓
Top SchoolJulien Herzen is a senior engineering manager at Isomorphic Labs with 11 years of experience bridging research-grade ML and production engineering. With a PhD in network algorithms from EPFL and a background as a creator and core contributor to the popular Darts time-series forecasting library, he blends deep academic rigor with pragmatic software design. He has hands-on expertise in Python, PyTorch and scikit-learn, and a track record of designing modular architectures, robust backtesting, and high-quality test suites for ML systems. Julien’s career includes international research placements and industry roles that reflect a comfort moving between exploratory research and shipping reliable products. Based in Lausanne, he is known for turning complex time-series and forecasting problems into usable tooling that accelerates model selection and evaluation.
11 years of coding experience
5 years of employment as a software developer
PhD, Network algorithms, PhD, Network algorithms at Ecole polytechnique fédérale de LausanneMaster of Science - MS, Communication systems, Master of Science - MS, Communication systems at EPFL (École polytechnique fédérale de Lausanne)
French, English, German
Stackoverflow
151reputation
7kreached
6answers
0questions
Github Skills (21)
python10
model-driven10
scikit10
machine-learning10
time-series10
backtesting10
backtest10
forecasting10
model-building10
scikit-learn10
forecast10
modeling10
model-driven-development10
data-analysis10
pytorch9
Programming languages (7)
Github contributions (5)
unit8co/darts
Sep 2018 - Jan 2023
A python library for user-friendly forecasting and anomaly detection on time series.
Role in this project:
Back-end Developer & Data Scientist
Back-end Developer & Data ScientistContributions:1027 reviews, 1473 commits, 433 PRs in 4 years 5 months
Contributions summary:Julien contributed to the development of a time series forecasting library, "darts", by implementing various machine learning models and backtesting functionalities. Their work included the design of a modular architecture for time series models, with an emphasis on model selection and evaluation. They focused on incorporating and extending existing forecasting models, primarily implementing new features with Python, scikit-learn and PyTorch, while maintaining code quality through testing.
forecastingpython-libraryanomalypythontime-series-analysis
hrzn/hrzn.github.io
Nov 2019 - Nov 2024
Contributions:14 pushes, 1 branch in 5 years 1 month
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.