Vladimir Iashin
Deep Learning Engineer at Revolut
Oxford, England, United Kingdom
Summary
👤
Senior🎓
Top SchoolVladimir Iashin is a deep learning engineer with nine years of experience, currently building foundational models for transaction systems at Revolut. He brings strong academic rigor from a postdoctoral stint at Oxford VGG and a PhD from Tampere, where he led multiple multi-modal vision and audio projects. His work spans open-set animal face recognition, audio-visual synchronization, and video-to-audio generation, with publications at ICASSP, ICIP-CW and GCPR and a public chimpanzee multi-modal dataset he helped curate and release. Skilled at moving research into reproducible code and infrastructure, he single-handedly developed codebases and managed multi‑GPU clusters during his PhD. Vladimir also mentors students and organizes research seminars, combining hands-on engineering with community-building. He is equally comfortable tackling applied industry problems and pushing boundaries in multi-modal machine learning research.
10 years of coding experience
7 years of employment as a software developer
Master of Science (with distinction) Applied Mathematics and Computer Science, Master of Science (with distinction) Applied Mathematics and Computer Science at Higher School of EconomicsDoctor of Philosophy PhD (with distinction) Electrical Engineering and Computer Science, Doctor of Philosophy PhD (with distinction) Electrical Engineering and Computer Science at Tampere University
Github Skills (182)
visual-studio-code-extension10
vowpal-wabbit10
lan10
parallel10
feature-extraction10
python10
pyaudioanalysis10
style-transfer10
deep-learning10
speech10
gpu10
rgb10
backend10
flask10
convolutional-neural-networks10
Programming languages (9)
Github contributions (5)
v-iashin/SpecVQGAN
Oct 2021 - Jun 2022
Source code for "Taming Visually Guided Sound Generation" (Oral at the BMVC 2021)
Contributions:20 commits, 13 pushes, 56 comments in 7 months
transformervqvaeganpytorchaudio-generation
v-iashin/CS231n
Apr 2018 - Jan 2021
PyTorch/Tensorflow solutions for Stanford's CS231n: "CNNs for Visual Recognition"
Contributions:40 commits, 16 PRs, 31 pushes in 2 years 10 months
cs231npytorchtensorflowvisual-recognitioncomputer-vision
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.