Mikhail Arkhipov
Software Architect at MIGx
Espoo, Finland
Summary
🤩
Rockstar🎓
Top SchoolMikhail Arkhipov is a pragmatic software architect with over a decade of hands-on experience designing and delivering enterprise-grade web systems using .NET, cloud, and container technologies. He combines system requirements definition, UML-driven architecture and technical leadership for small teams with a proven track record in Banking, Telecom, Pharmaceuticals and supply-chain projects. Skilled in CI/CD, single-click deployments and reliability-driven design, he has repeatedly simplified support and sped up releases through architecture and process improvements. Beyond .NET stacks he has contributed to open-source NLP tooling—improving NER models and adding multilingual BERT support to the widely used DeepPavlov project—showing a practical interest in applied ML. Based in Espoo, he focuses on finding simple, robust solutions in ambiguous situations and mentoring teams to leverage their strengths.
10 years of coding experience
16 years of employment as a software developer
MCSD, .net development, MCSD, .net development at MS CourcesSaint Petersburg State Electrotechnical University "LETI"
English, Russian
Github Skills (6)
machine-learning10
nlp10
tensorflow10
python10
bert10
computer-engineering8
Programming languages (4)
Github contributions (5)
deeppavlov/DeepPavlov
Jan 2018 - May 2019
An open source library for deep learning end-to-end dialog systems and chatbots.
Role in this project:
ML Engineer
ML EngineerContributions:333 commits, 44 PRs, 380 pushes in 1 year 3 months
Contributions summary:Mikhail primarily contributed to the development and enhancement of Named Entity Recognition (NER) models within the DeepPavlov library. Their work included adding a separate NER model, moving the NER network for Slot Filling to a dedicated module, and incorporating character embeddings. Furthermore, they added features like capitalization and the ability to process multilingual data within the NER framework, as evidenced by the addition of multilingual BERT support. The user also implemented critical changes to ensure correct functionality including bug fixes to the NER inference process.
dialog-systemsdialogue-managerbotintent-classificationdialogue-systems
deeppavlov/ner
Sep 2017 - Oct 2018
Named Entity Recognition
Contributions:39 commits, 2 PRs, 70 pushes in 1 year 1 month
nlpnamed-entity-recognitionnatural-language-understandingentity-recognitiondeep-learning
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.