Anton Emelyanov

email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

🤩
Rockstar
Anton Emelyanov is a software engineer with nine years of experience building production-grade systems across major tech companies and startups, currently at Utopai Studios. He combines practical engineering at companies like Google, AWS, and FlutterFlow with research-minded work as an Amazon CodeGuru research engineer, bringing strong expertise in Python and NLP. Anton contributes to open-source NLP projects—most notably improving Russian GPT-3 tooling in the ai-forever/ru-gpts repo—demonstrating hands-on model fine-tuning and generation pipelines. His academic background is a Master’s in Computational Mathematics and Cybernetics from MSU, underpinning a rigorous approach to algorithmic problems and model debugging. Comfortable bridging research and product teams, he has a track record of shipping robust ML integrations and fixing complex distributed-model issues. Based in the United States, he blends deep technical craft with practical delivery across cloud and ML stacks.
code9 years of coding experience
github-logo-circle

Github Skills (14)

text-generation10
huggingface-transformers10
pytorch10
machine-learning10
nlp10
trainings10
python10
modeling10
gpt9
shell8
script8
sh8
scripting8
deepspeed7

Programming languages (4)

C++TeXJupyter NotebookPython

Github contributions (5)

github-logo-circle
ai-forever/ru-gpts

Oct 2020 - Dec 2022

Russian GPT3 models.
Role in this project:
userML Engineer
Contributions:69 commits, 14 PRs, 120 pushes in 2 years 2 months
Contributions summary:Anton contributed to the `ru-gpts` repository, which focuses on Russian GPT3 models. Their work involved modifying the `generate_transformers.py` script, likely to refine the text generation process, incorporating clearer prompts. They also updated scripts related to pretraining the models, and fixed errors related to different model parallel unit (mpu) configurations. Furthermore, they provided example code for finetuning and generating text with the RuGPT3 models using Hugging Face Transformers.
pytorchnlpnatural-language-processinggpt3
king-menin/nlp-course

Apr 2018 - May 2018

Contributions:27 commits, 22 pushes, 1 branch in 1 month
javascript
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
Anton Emelyanov