Taras Kucherenko
ML Research Scientist III at SEED (Electronic Arts)
Stockholm, Sweden
Summary
👤
Senior🎓
Top SchoolTaras Kucherenko is an ML Research Scientist III at EA SEED in Stockholm with a decade of experience building machine learning systems for character animation and non-verbal behavior generation. He combines deep research expertise from a PhD at KTH on generative models for gestures and facial expressions with hands-on product impact, having led projects that halved operational costs using deep learning and signal processing. His work spans industry labs including Microsoft and EA, where he blends R&D engineering, project leadership, and team management to move research into production. He has taught machine learning courses and advised startups on applied classification and speech-quality feedback systems, reflecting a strong practical bent alongside academic rigor. Fluent in signal-processing-driven ML and simulation sciences, Taras excels at making probabilistic generative models work in real-time animation pipelines. A detail that sets him apart is his consistent focus on non-verbal behavior modeling—hand gestures in particular—which makes his research directly valuable for more expressive virtual characters.
10 years of coding experience
6 years of employment as a software developer
Doctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at KTH Royal Institute of TechnologyKiev-Pecherskiy Liceum 171 "Lider"Master's degree, Simulation Sciences, Master's degree, Simulation Sciences at RWTH Aachen UniversityIgor Sikorsky Kyiv Polytechnic Institute
Russian, English, French, Spanish, Ukrainian, Swedish, German
Stackoverflow
113reputation
19kreached
8answers
5questions
Github Skills (171)
parallel10
python10
gesture10
classifier10
marker10
representations10
deep-learning10
gpu10
wordnet10
ray10
optimization10
glove10
autoencoder10
document-classification10
gestures10
Programming languages (5)
Github contributions (5)
Svito-zar/gesticulator
Aug 2020 - May 2022
This is the official implementation for the ICMI 2020 paper "Gesticulator: A framework for semantically-aware speech-driven gesture generation"
Contributions:50 commits, 6 PRs, 19 pushes in 1 year 9 months
gesture-generationgesturespeech
Svito-zar/Speech_driven_gesture_generation
Jan 2019 - May 2022
This is an obsolete and not maintained implementation for the paper "Should Beat Gestures Be Learned or Designed? A Benchmarking User Study", which is based on the paper "Analyzing Input and Output Representations for Speech-Driven Gesture Generation". For the up to date code we refer to the repo from which this code was forked
Contributions:4 PRs, 25 pushes, 11 branches in 3 years 3 months
analyzingbenchmarkingrepresentationslearneduser-study
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.