Viacheslav Kovalev is a Machine Learning Engineer with 11 years of engineering experience who blends production-grade backend skills (Python, FastAPI, Docker, Postgres) with strong applied ML expertise (CatBoost, LightGBM, PyTorch, transformers). He has shipped recommender systems and RAG/S2T knowledge pipelines—building a FastAPI-based post recommendation service that leverages DistilBERT embeddings and A/B testing to drive measurable improvements. At Carlsberg he boosted forecast accuracy by 15% through time-series modeling and SQL optimization, and at UPlineSoft he engineered asynchronous VK bots, Prometheus metrics, and S3-integrated pipelines for real-world deployment. He also contributes to open-source tooling, improving profile management and dependency handling in the widely used Erlang rebar3 project. Comfortable moving between feature engineering, model tuning (Optuna) and infra concerns, he brings a pragmatic, data-oriented approach shaped by both ML internships and earlier engineering roles in petrochemical process optimization.
11 years of coding experience
3 years of employment as a software developer
Master of Engineering - MEng, ENGINEERING, Excellent, Master of Engineering - MEng, ENGINEERING, Excellent at National mineral resources university (University of mines)
Machine Learning Engineer, Data Science, Successful Graduate, Machine Learning Engineer, Data Science, Successful Graduate at Karpov Courses Data Science School
Erlang build tool that makes it easy to compile and test Erlang applications and releases.
Role in this project:
Back-end Developer
Contributions:35 commits, 13 PRs, 58 comments in 3 months
Contributions summary:Viacheslav primarily contributed to the improvement of the Erlang build tool, rebar3. Their work focused on enhancing the profile management features, including correcting profile deduplication logic and implementing tests for it. Furthermore, the user fixed a typo in an error message and made changes related to git dependency fetching. These changes suggest a focus on improving the tool's build process and dependency management.
Contributions:1 release, 132 commits, 1 tag in 2 months
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.
Request Free Trial
Viacheslav Kovalev - Machine Learning Engineer at UPlineSoft