Intro
Hey! I’m a research engineer with 8 years of experience in speech processing, endorsed as an Exceptional Talent (UK Global Talent Visa) for achievements and leadership in the field. I have delivered State-of-the-Art speaker recognition research, won world voice biometrics championships, and shipped production systems for on-device speaker recognition and AI voice assistants. I love being in Day 1 mode, and my current research interests include multi-modal and generative speech applications.
Professional experience
- AI Voice Assistant at TBC Uzbekistan
- 06/2025 - present: Machine Learning Engineer
- Building streaming speech-to-speech AI voice assistant in Russian and Uzbek languages for digital banking
- Voice Biometrics at ID R&D Inc.
- 08/2021 - 12/2024: Machine Learning Teamlead
- Speaker recognition for IoT devices
- Voice antispoofing and deepfakes detection
- 11/2019 - 08/2021: Machine Learning Engineer
- Speaker identification and speaker diarization for callcenters
- Automatic Speech Recognition at MTS AI
- 10/2018 - 11/2019: Machine Learning Developer
- Mathematical Modelling at Center of Underground Navigation
- 08/2016 - 08/2017: Junior Engineer
- Kalman filtering for gas pipeline mapping
Teaching
- Speech Recognition and Generation at AI Talent Hub, ITMO University
- 02/2025 - present: Course Lead
- Machine Learning and Data Mining at SPbU
- 10/2019 - 06/2023: Course Lead
- Course Leader for Machine Learning and Data Mining courses
- Supervision of 7 MSc students graduation projects
Trainings
Education
- 09/2017 - 09/2018: MSc Data Science
- 09/2013 - 09/2017: BSc Control Systems
Designed by Ankit Sultana, adapted by Jee-weon Jung and re-used by Anton Okhotnikov.