Julian Peller
Lead Data Scientist
Buenos Aires, Autonomous City of Buenos Aires, Argentina
Summary
👤
Senior🎓
Top SchoolJulian Peller is a Lead Data Scientist with 13 years of experience building and shipping ML and DL systems across healthcare, gaming, finance, and recommender platforms. He currently leads multi-disciplinary teams at EverythingALS/Humai developing multimodal digital biomarkers for early ALS diagnosis and progression tracking, combining audio-visual feature engineering with architectures from CNNs and LSTMs to VideoMAE and Wav2Vec2. Comfortable from kernel-level software automation to production ML, he has a strong track record of improving production metrics (e.g., large CTR gains from recommender work) and optimizing inference and deployment pipelines. His hands-on stack centers on Python, PyTorch and HuggingFace, with experience across AWS, GCP, Azure and observability tools like WandB. An active educator and contributor, he authored practical Jupyter notebooks on Shapley values and anomaly detection for Humai’s public course materials, reflecting a penchant for making complex techniques approachable. Based in Buenos Aires, he pairs academic rigor from a UBA MS with pragmatic engineering that moves research models into robust, measurable production outcomes.
13 years of coding experience
15 years of employment as a software developer
Master of Science (MS) Computer Science, Master of Science (MS) Computer Science at University of Buenos Aires
Spanish, English
Stackoverflow
3,347reputation
682kreached
85answers
0questions
machine-learning
top-5%
python
top-5%
Github Skills (20)
shap10
python10
data-science10
scikit10
pandas10
machine-learning10
deep-learning10
scikit-learn10
matplotlib9
seaborn9
xgboost9
numpy9
google-colab8
keras6
anaconda6
Programming languages (3)
Github contributions (5)
institutohumai/cursos-python
Jul 2022 - Sep 2022
Cursos completos de IA dictados por Humai
Role in this project:
Data Scientist
Data ScientistContributions:9 commits, 5 PRs in 2 months
Contributions summary:Julian's contributions focused on machine learning tasks within the repository. They added and updated Jupyter notebooks related to Shapley values and anomaly detection, including example exercises. The user also demonstrated skills in data analysis and manipulation, loading and describing datasets, and visualizing target variable distributions within the context of a data science project.
cursospythonpordata-sciencedeep-learning
dataista0/making-a-nietzsche
Aug 2019 - Jun 2021
Contributions:27 commits, 25 pushes, 1 branch in 1 year 9 months
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.