Viktor Yershov
Senior Software Engineer at Spice AI
Seattle, Washington, United States
Summary
🤩
Rockstar🎓
Top SchoolViktor Yershov is a Senior Software Engineer based in Seattle with 10 years of experience building data-intensive systems and production ML tooling across Google, Uber, and startup environments. He blends a functional-programming mindset with practical ML deployment expertise, having contributed to model-to-code tooling that translates trained models into native languages for zero-dependency inference. At companies from EPAM to Spice AI he has shipped backend and data engineering solutions at scale, moving from Python-focused data pipelines to senior roles driving cross-platform compatibility and performance. Viktor’s background spans both engineering leadership and hands-on implementation, often refactoring large codebases to introduce cleaner exporter/generator abstractions. He holds a Computer Science degree from Donetsk National University and brings a pragmatic focus on translating models into reliable, production-ready services.
10 years of coding experience
11 years of employment as a software developer
Bachelor's degree MS Computer Science, Bachelor's degree MS Computer Science at Donetsk National University
Английский
Stackoverflow
331reputation
13kreached
5answers
10questions
Github Skills (18)
python10
scikit10
machine-learning10
java10
javas10
code-generation10
scikit-learn10
model-conversion10
flink-streaming6
google-cloud-pubsub6
tensorflow6
lightgbm6
jython6
google-cloud-platform6
apache-flink6
Programming languages (3)
Github contributions (5)
BayesWitnesses/m2cgen
Jan 2019 - Feb 2019
Transform ML models into a native code (Java, C, Python, Go, JavaScript, Visual Basic, C#, R, PowerShell, PHP, Dart, Haskell, Ruby, F#, Rust) with zero dependencies
Role in this project:
ML Engineer
ML EngineerContributions:39 commits, 93 PRs, 270 pushes in 1 month
Contributions summary:Viktor's contributions primarily focus on transforming machine learning models into native code. They initiated the implementation of `model2ast`, creating a Python-based example using `scikit-learn` for linear regression and defining model conversion classes. The user further implemented Java if statements within the code generation process and introduced significant refactoring by integrating exporters and code generators. These changes indicate a focus on model deployment and cross-platform compatibility, key for ML engineers.
xgboostdependenciespythonml-modelslightgbm
krinart/twitter-realtime-pipeline
Nov 2019 - Nov 2019
Contributions:19 commits, 16 pushes in 4 days
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.