Sanjar Lov
Data Scientist Machine Learning Engineer
Tashkent Region, Uzbekistan
Summary
👤
Senior🎓
Top SchoolSanjar Lov is a Data Scientist and Machine Learning Engineer with a decade of experience building production-grade AI systems across research and industry, currently driving graph- and SLAM-focused optimization for large-scale warehouse automation at EPAM. He has strong roots in computational chemistry and drug design, where he developed generative deep learning frameworks and published libraries that achieved state-of-the-art molecular modeling results. At Alif Uzbekistan he architected an end-to-end ML ecosystem (GulChatAI) delivering near-real-time conversational automation, credit scoring, OCR and fraud detection with robust MLOps and annotation tooling. Sanjar blends research-grade model development (GNNs, autoregressive and autoencoding models) with practical engineering—API integrations, scalable refactors, and monitoring—that materially improved latency, scalability and business metrics. Based in Tashkent, he is an active open-source contributor focused on ML tooling for drug discovery and other applied domains.
9 years of coding experience
8 years of employment as a software developer
Bachelor's degree, Applied Mathematics, Bachelor's degree, Applied Mathematics at Branch of Lomonosov Moscow State University in Tashkent
English, Russian, Uzbek
Stackoverflow
1,079reputation
56kreached
40answers
2questions
scikit-learn
top-5%
Github Skills (43)
notebook10
pytorch10
kaggle10
python10
data-science10
mxnet-gluon10
scikit10
statistics10
mxnet10
machine-learning10
recurrent-neural-networks10
gluon10
reinforcement-learning10
gaussian-processes10
hyperparameter-optimization10
Programming languages (2)
Github contributions (5)
sanjaradylov/scikit-fallback
Jun 2024 - Mar 2025
Machine Learning with a Reject Option
Contributions:4 releases, 30 PRs, 57 pushes in 8 months
fallback-classificationmachine-learningscikit-learnselective-classification
sanjaradylov/moleculegen-ml
Dec 2019 - May 2022
Generate novel molecules using neural language models
Contributions:4 releases, 19 reviews, 232 commits in 2 years 5 months
cheminformaticslanguage-modelchemistrymxnetmolecules
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.