Pantelis Elinas
NLP ML Researcher at UNSW
Sydney, New South Wales, Australia
Summary
🤩
Rockstar🎓
Top SchoolPantelis Elinas is an NLP and ML researcher based in Sydney with 8 years of professional experience and a PhD in Computer Science from UBC. He has led teams and applied research at CSIRO's Data61 and transitioned into industry roles as an AI/ML engineer before taking an academic research position at UNSW. His work spans graph machine learning, NLP, computer vision and robotics, and includes notable open-source contributions to the stellargraph library where he implemented performance-critical Cluster GCN layers and generators. As a principal engineer and team leader he blends hands-on model development with delivery of production-ready systems and cross-disciplinary collaboration. Pantelis is comfortable moving between deep research and applied engineering, often optimizing core graph-processing operations that improve scalability in real-world ML pipelines.
8 years of coding experience
17 years of employment as a software developer
Doctor of Philosophy (Ph.D.) Computer Science, Doctor of Philosophy (Ph.D.) Computer Science at The University of British ColumbiaBachelor of Science (B.Sc.) Space and Communication Sciences, Bachelor of Science (B.Sc.) Space and Communication Sciences at York University
Github Skills (9)
data-generation10
keras10
machine-learning10
tensorflow10
graph-neural-network10
python10
refactor9
computer-engineering9
refactoring9
Programming languages (2)
Github contributions (5)
stellargraph/stellargraph
May 2018 - May 2020
StellarGraph - Machine Learning on Graphs
Role in this project:
ML Engineer & Data Scientist
ML Engineer & Data ScientistContributions:1037 commits, 53 PRs, 319 pushes in 2 years
Contributions summary:Pantelis's commits primarily focused on implementing and testing classes related to graph machine learning, with a specific focus on methods related to graph representation learning and supervised graph classification. These commits included the development of a Cluster GCN layer and related generator implementations within the stellargraph library. The contributions are centered on enhancing the library's capabilities for graph-based analysis and learning, with a focus on a performance-critical component of this approach, namely the graph processing operation's efficiency.
pythonheterogeneous-networkssaliency-mapfraud-preventiongraph-machine-learning
stellargraph/stellar-practical-ml-on-graphs
Jan 2019 - Mar 2020
Course titled Practical Machine Learning on Graphs
Contributions:70 commits, 1 PR, 34 pushes in 1 year 1 month
practical-machine-learningdata-sciencemachine-learningpracticalgraphs
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.