Stepan Komkov
Principal Software Engineer at Yandex
Belgrade, Central Serbia
Summary
👤
Senior🎓
Top SchoolStepan Komkov is a Principal Software Engineer and deep learning researcher with nine years of experience building state-of-the-art ML systems, currently driving emotional speech synthesis at Yandex. He holds a PhD in Discrete Mathematics and Mathematical Cybernetics from MSU and combines rigorous theoretical foundations with hands-on R&D that has led to multiple top-1 benchmark results in trajectory prediction, video action recognition, and text-to-video retrieval while at Huawei. Stepan has a track record of shipping high-impact, published features—most recently the empathic smart speaker—and holds patents improving face recognition robustness. He mentors teams and presents research publicly, blending academic rigor with product-focused engineering. Based in Belgrade, he brings rare cross-domain expertise spanning speech, vision, and trajectory forecasting, often turning competitive benchmark wins into deployable solutions. A curious polymath, his GitHub bio hints at a playful personal side beyond his technical accomplishments.
9 years of coding experience
5 years of employment as a software developer
Lomonosov Moscow State University
English, Russian, Serbian
Github Skills (8)
adversarial-attacks9
nvidia-jetson-nano7
arcface7
acceleration5
video-understanding4
low-latency3
tensorflow1
softmax1
Programming languages (2)
Github contributions (5)
papermsucode/advhat
Aug 2019 - Feb 2021
AdvHat: Real-world adversarial attack on ArcFace Face ID system
Contributions:11 commits, 11 pushes, 25 comments in 1 year 6 months
adversarial-attacksarcface
papermsucode/mutual-modality-learning
Nov 2020 - Mar 2021
Mutual Modality Learning code
Contributions:2 commits, 3 pushes, 2 comments in 3 months
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.