Yuri Baburov
Chief Technology Officer at DocuTable
San Francisco, California, United States
Summary
🤩
Rockstar🎓
Top SchoolYuri Baburov is a CTO and AI/ML specialist with 19 years of experience building content-rich web platforms, search and recommendation systems, and production-grade deep learning solutions from San Francisco. He combines hands-on expertise in Python, Django, PyTorch and frontend frameworks like Vue/React with a long track record of consulting and startup advising across NLP, speech recognition and semantic search. Yuri authored and improved open-source tooling such as a high-performance python-readability parser, demonstrating pragmatic attention to real-world data extraction and encoding issues. He teaches deep learning at Novosibirsk State University and has led teams delivering the world’s largest annotated speech corpus and enterprise chatbots and helpdesks. Comfortable moving between research and product, he excels at turning large, messy information sources into user-facing, searchable knowledge products.
19 years of coding experience
18 years of employment as a software developer
Engineer, Information Technologies, Engineer, Information Technologies at Novosibirsk State University (NSU)
Russian, English
Stackoverflow
722reputation
68kreached
10answers
2questions
Github Skills (12)
html-parsing10
python10
lxml10
regular-expression9
api-design8
php6
javascript6
pyyaml6
wikipedia6
yaml6
wikimedia-commons6
heuristics6
Programming languages (8)
Github contributions (5)
buriy/python-readability
May 2011 - Dec 2022
fast python port of arc90's readability tool, updated to match latest readability.js!
Role in this project:
Back-end Developer
Back-end DeveloperContributions:6 releases, 133 commits, 60 PRs in 11 years 9 months
Contributions summary:Yuri primarily contributed to improving the `python-readability` project, a fast Python port of the readability tool. Their work involved migrating the codebase to use `lxml` for HTML parsing, which enhanced encoding recognition. They also improved the title shortening method, adding it to the `Document` class and updated the scoring algorithm to align with `readability.js` v1.7.1. Moreover, they enhanced the code with a series of bug fixes and minor adjustments.
python
buriy/asr_eval
Nov 2019 - Sep 2022
Russian ASR Evaluation
Contributions:9 commits, 7 PRs, 11 pushes in 2 years 10 months
asr
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.