Summary
Semyon Polyakov is a Senior Machine Learning Engineer with 11 years of experience designing and deploying high-throughput ML systems for NLP, recommendation systems, and generative models, now based in Dublin and currently at Intercom. He has led teams at VKontakte to build thematic recommendation feeds and content-analysis pipelines that served millions daily, delivering measurable business impact (e.g., +5% comments, multi-percent engagement lifts) while keeping per-item latency in the tens of milliseconds. His toolkit spans deep learning (BERT, ELMo, transformers), multimodal models, probabilistic and uplift modelling, and scalable ranking/recommendation approaches (iALS, DSSM, XGBoost, Mult-VAE). Semyon pairs rigorous A/B testing and statistical significance practices with production engineering—shipping dozens of models and an MVP feature store—and has presented and published research at conferences. He stays current by reading arXiv and top-conference work, and an under-the-radar strength is his track record of building efficient backends (3000 qps single-server designs) that enabled rapid feature launches.
11 years of coding experience
7 years of employment as a software developer
Master's degree Software Engineering, Master's degree Software Engineering at Saint Petersburg Academic University
Bachelor's degree Computer Science, Bachelor's degree Computer Science at Tyumen State University
Russian, English