Geoff Jarrad
Senior Data Scientist
Adelaide, South Australia
Summary
🤩
RockstarGeoff Jarrad is a Senior Data Scientist based in Adelaide with six years of hands-on experience building ML solutions and research-grade tooling. He blends practical data science with engineering rigor, contributing to the popular StellarGraph library where he implemented directed GraphSAGE and sampling, fixed dataset issues, and refactored model components for consistency. Comfortable moving between prototyping and production-ready code, he has a strong grasp of graph algorithms and their real-world application. Geoff’s open-source work shows attention to reproducibility and usability—adding example notebooks and unifying activations and regularizations to help other practitioners.
6 years of coding experience
Github Skills (14)
algorithm10
geometric-deep-learning10
graphdb10
keras10
machine-learning10
machine-learning-algorithms10
networkx10
tensorflow10
graph-neural-network10
graphml10
python10
data-science10
deep-learning9
graph-analysis9
Programming languages (1)
Github contributions (3)
stellargraph/stellargraph
Jul 2019 - Dec 2019
StellarGraph - Machine Learning on Graphs
Role in this project:
ML Engineer & Data Scientist
ML Engineer & Data ScientistContributions:18 commits, 25 PRs, 81 pushes in 5 months
Contributions summary:Geoff contributed to the development and maintenance of the StellarGraph library, focusing on machine learning models for graph analysis. They addressed issues related to the Cora dataset, ensuring correct edge directions and data loading. The user implemented and tested directed breadth-first search sampling and directed GraphSAGE, demonstrating an understanding of graph algorithms and machine learning techniques. Furthermore, the user refactored code, unified activation functions and regularizations across various models, and added example notebooks.
pythonheterogeneous-networkssaliency-mapfraud-preventiongraph-machine-learning
stellargraph/AMLSim
Feb 2020 - Feb 2020
This project is intended to provide a multi-agent based simulator that generates a series of banking transaction data together with a set of known money laundering patterns. We welcome you to enhance this effort since data set is critical to advance our detection capabilities of money laundering activities
Contributions:2 PRs, 1 push, 2 branches in 6 days
criticalagent-basedeffortagentdata-set
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.