Efthymios Tzinis
Senior Research Scientist at Google
Cambridge, Massachusetts, United States
Summary
👤
Senior🎓
Top SchoolEfthymios Tzinis is a senior research scientist at Google with nine years of experience specializing in audio-visual perception, sound separation, and on-device audio generation for Pixel devices. He earned a PhD in Computer Science from UIUC and previously contributed research at MERL and Meta Reality Labs, with a past Google PhD Fellowship recognizing his work. Efthymios has a strong track record of turning cutting-edge research into deployable features, leading a team that prototypes and ships new audio models for mobile inference. His background blends deep academic rigor with practical ML engineering—he has repeatedly improved state-of-the-art source separation methods and built robust testable codebases during multiple Google internships. Based in Cambridge, MA, he brings both systems-level thinking and hands-on experimentation, often exploring unsupervised and multimodal approaches that reduce reliance on labeled data.
9 years of coding experience
6 years of employment as a software developer
High School, High School at Arsakeio Tositseio EkalisDoctor of Philosophy - PhD Computer Science (Artificial Intelligence), Doctor of Philosophy - PhD Computer Science (Artificial Intelligence) at University of Illinois Urbana-ChampaignDiploma - MEng Computer Science, Diploma - MEng Computer Science at National Technical University of Athens
English, Greek
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (20)
downsampling10
speech-enhancement10
resampling10
audio10
speech10
source-separation10
pytorch9
deep-learning9
clustering9
frontend9
autoencoder7
federated-learning7
recurrence5
toolbox4
python3
Programming languages (2)
Github contributions (5)
etzinis/sudo_rm_rf
Nov 2019 - Apr 2022
Code for SuDoRm-Rf networks for efficient audio source separation. SuDoRm-Rf stands for SUccessive DOwnsampling and Resampling of Multi-Resolution Features which enables a more efficient way of separating sources from mixtures.
Contributions:192 commits, 50 pushes, 1 branch in 2 years 5 months
audiodownsamplingresamplingsource-separationdeep-learning
etzinis/heterogeneous_separation
Mar 2022 - Dec 2022
Code and data recipes for the paper: Heterogeneous Target Speech Separation
Contributions:28 commits, 2 PRs, 17 pushes in 8 months
speech
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.