Artur Paniukov
AI Frameworks Engineer at Intel Corporation
Dublin, Ireland
Summary
🤩
Rockstar🎓
Top SchoolArtur Paniukov is an AI Frameworks Engineer at Intel with six years of experience building NLP and multimodal inference tooling that bridges research and production. He designs and implements text-processing extensions for OpenVINO, including a HuggingFace tokenizers parser and tokenizer utilities for model merging and sampling, and contributes practical notebooks that showcase CLIP-based language-visual saliency accelerated with OpenVINO. Previously he delivered NLP model conversion, dataset/tokenizer pipelines and automatic notebook generation for OpenVINO’s Deep Learning Workbench, and before that built production-grade ML services and POCs across document understanding, math solvers and automation at EPAM. Based in Dublin, he combines applied mathematics training with hands-on engineering to optimize transformer workloads and developer workflows, and often surfaces non-obvious gains by integrating tokenizer-level ops into inference pipelines.
6 years of coding experience
3 years of employment as a software developer
Applied Mathematics, Applied Mathematics at Saint Petersburg State UniversityBachelor's degree Applied Mathematics, Bachelor's degree Applied Mathematics at Herzen State Pedagogical University of Russia
Russian, English
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (8)
computer-vision10
machine-learning10
deep-learning10
inference10
python10
openvino10
transformers9
pytorch9
Programming languages (4)
Github contributions (5)
openvinotoolkit/openvino_notebooks
Jan 2023 - Sep 2024
📚 Jupyter notebook tutorials for OpenVINO™
Role in this project:
ML Engineer
ML EngineerContributions:46 reviews, 4 PRs, 47 comments in 1 year 7 months
Contributions summary:Artur implemented a notebook for generating language-visual saliency maps using CLIP and OpenVINO™. The notebook demonstrates how to apply CLIP for image analysis and provides insights into visualizing the regions of an image most relevant to a given text query. The contributions involve integrating CLIP with OpenVINO™ to speed up inference and enhance the performance of the saliency map generation process. The commits focus on code examples to achieve visual saliency and a better understanding of the image.
deep-learningjupyter-notebooknotebookinferencecomputer-vision
apaniukov/openvino
Nov 2021 - Mar 2025
OpenVINO™ Toolkit repository
Contributions:70 pushes, 5 branches in 3 years 4 months
pytorchdeep-learninggpuopenvino-toolkitcomputer-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.