EleniĀ Triantafillou
Research Scientist at Google
United Kingdom
Summary
š¤
Seniorš
Top SchoolEleni Triantafillou is a research scientist at Google Brain with 11 years of experience combining rigorous academic training (PhD, University of Toronto & Vector Institute) and hands-on engineering to build adaptable learning systems. Her work focuses on few-shot and meta-learning, including co-creating the influential Meta-Dataset benchmark and improving practical baselines like MAML and finetuning to work across diverse architectures and Mini-ImageNet evaluations. She brings a rare blend of theoretical inquiry into representations that enable fast generalization and pragmatic code contributions that make research reproducible and extensible. Based in the UK, Eleni has a strong teaching background and a track record of internships and research roles across top labs, reflecting both depth and breadth in ML research. A detail that often surprises collaborators: she routinely bridges research and software engineering by refactoring core training interfaces to accelerate experimentation at scale.
11 years of coding experience
2 years of employment as a software developer
High School Diploma, 97%, High School Diploma, 97% at Experimental High School of the University of PatrasBachelor's degree, Computer Science, 3.76 / 4 (top 2%), Bachelor's degree, Computer Science, 3.76 / 4 (top 2%) at University of Toronto
Github Skills (8)
meta-learning10
machine-learning10
benchmark10
benchmarking10
tensorflow10
python10
few-shot-learning10
resnet9
Programming languages (4)
Github contributions (5)
google-research/meta-dataset
Aug 2019 - Mar 2022
A dataset of datasets for learning to learn from few examples
Role in this project:
ML Engineer
ML EngineerContributions:1 review, 26 commits, 1 PR in 2 years 7 months
Contributions summary:Eleni made significant contributions to the `meta-dataset` repository, focusing on improving the `Finetune` and `MAML` baselines. They added functionality to finetune all layers instead of just a linear layer, refactored and unified interfaces of MAML architectures, and modified the code related to the ResNet and four_layer_convnet architectures. The user also made changes to support Mini-ImageNet evaluation by modifying gin files to incorporate different configurations for evaluating the model on the Mini-ImageNet dataset.
meta-learningdatasetmachine-learningbenchmarklearning-to-learn
google-research/perch
Jun 2022 - Feb 2023
Contributions:29 commits in 7 months
Find and Hire Top DevelopersWeāve 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.