Artur
Sogomonyan
Data Scientist
Machine Learning Engineer
Computer Vision
Deep Learning
Full-stack development
-
ReelMate
Developed an AI-driven platform that streamlines the creation and distribution of short-form video content across major social media platforms. Engineered features to transform text-based content into engaging videos, automate cross-platform scheduling, and provide analytics to optimize engagement. Integrated a Telegram bot to facilitate seamless content approval workflows. Utilized FastAPI and AsyncIO to ensure high-performance, real-time operations.
FastAPIAsyncIOOpenAISocialMediaAutomation
AIM Hackathon - TIMETOACT Group 2nd Place Winner
A platform with Retrieval-Augmented Generation (RAG) to identify greenwashing in ESG reports.
RAGESGLangChainFlaskOpenAI
susteam - Full-stack development of ESG platform
Architecture and development of the ESG platform for generating sustainability reports in the hospitality industry.
Full-stackESGReact.jsFastAPIBERTLLama3
Rail4Future Data Science Project 2024
Analyzing rail irregularities for industrial partners Siemens and ÖBB.
LSTMTensorflowDataScience
Full-stack Development of the NFT Platform
Implemented a secure authentication system using MetaMask, which allows users to store and manage seed phrases as encoded NFTs. Developed the platform’s backend to interact seamlessly with the Polygon blockchain, ensuring efficient and secure transactions.
NFTMetaMaskPolygonSolidityFull-stack
LawSyncr
Led the end-to-end full-stack development of the project, including the implementation of a Minimum Viable Product (MVP) with integrated machine learning components.
Full-stackMachine LearningRAGFlaskSvelteLLM
Crypto Trading Analysis and Future Trading
Engineered a bot to systematically scrape and collect trade data from Binance, allowing detailed real-time market analysis. Automated the execution of trading strategies using a custom-built bot, ensuring consistent and timely trades.
CryptoBinanceTradingFastAPIAsyncIO
Portfolio Website Development
Designed and developed a portfolio website, integrating continuous integration/continuous deployment (CI/CD) pipelines for seamless updates via GitHub Pages. Utilized Obsidian vault data to create an interactive front-end that visualizes my professional journey using graphology and sigma libraries.
CI/CDSvelteGitHub PagesGraphologySigma
Document Analysis and Optical Character Recognition (OCR)
Conducted a comprehensive layout analysis of historical documents, identifying key structural elements to improve text extraction accuracy. Integrated advanced Named Entity Recognition (NER) using SpaCy and fine-tuned language models (e.g., LLaMA-3) to extract metadata from images.
OCRTesseractSpaCyLLaMA-3Python
Lip Reading app for Austrian Red Cross
Developed a lip reading app using AV-HuBERT for the Austrian Red Cross to communicate in noisy environments. Integrated the model into a web app, passing the video stream from the smartphone to the model, reading the lips, and generating text.
Lip ReadingAV-HuBERTFastAPINext.jsMachine Learning
Data Pipeline and Knowledge Graph for Tourism
Implemented a data pipeline mapping data from different sources and building a knowledge graph for tourism subjects. Visualized the results as an interactive map with a chatbot to analyze points of interest.
Knowledge GraphSeleniumGeoandasFolium
GLOSAV - Machine learning analyst
Engineered a sophisticated algorithm to detect railway routes with object detection and tracking mechanisms. Developed a robust way to track obstacles on the rails.
Machine LearningYOLOv4OpenCVNumPy
Printerra
Diploma thesis ”3D printer failure detection system based on computer vision detection”.
Machine LearningOpenCVNumPyPython
Education
Master of Science
Data Science, Technische Universität Wien, 2022 - 2025
Bachelor of Science
Information technologies and telecommunications, Bauman Moscow State Technical University, 2014 - 2020
- Diploma thesis "3D printer failure detection system based on computer vision detection"
Work Experience
Data Scientist, Project Rail4Future
Technische Universität Wien, Feb 2024 - Jul 2024
- Analyzed rail irregularities, optimized LSTM models, and collaborated with Siemens and ÖBB.
- Performed significance tests and improved model robustness and performance.
CTO, Data Scientist
susteam, Jan 2023 - present
- Developed architecture and Full Stack ESG system with OCR, Data Analysis, and Machine Learning.
- Implemented RAG for LLMs using FastAPI, AWS, React.js, Bert, and LLama3.
Machine Learning Analyst
GLOSAV, Feb 2021 - Jul 2021
- Engineered algorithms for object detection and tracking in railway routes, contributing to a train autopilot system.
- Developed a robust method to track obstacles with performance under 5ms for real-time streaming.
Project Manager, 3D-Modeller, Software Engineer
Arterra Miniature, Feb 2020 - Mar 2021
- Handled 3D visualization, prototyping, and project management from inception to delivery.
Frontend Developer
KRK Group, Sep 2019 - Dec 2019
- Developed corporate educational platform, implemented React application, and UI design.
Full-Stack Developer
Linwood, Aug 2018 - Sep 2019
- Implemented online store development, testing, promotion, and business functionality expansion.
Web Developer
Freelance, Mar 2017 - Aug 2018
- Worked on front-end and back-end projects, developing and refactoring solutions for functionality extensions.
Skills
Software Development: Docker, Python, C++, R, Django, Flask, FastAPI, JavaScript, React, Svelte
Machine Learning: scikit-learn, Pandas, NumPy, Tensorflow, PyTorch, OpenCV, YOLO, NLTK, SpaCy, Bert, LLama3, GPT, LangChain
Databases and Cloud: Git, PostgreSQL, MongoDB, Redis, RabbitMQ, nginx, Gunicorn, Spark, AWS EC2, S3, Linux/Debian/Fedora
Languages: English (C1), German (A2), Russian (C2), Armenian (B2)
Projects and Awards
2nd Place Winner
AIM Hackathon - TIMETOACT Group, Oct 2024
- Developed a platform using Retrieval-Augmented Generation (RAG) to identify greenwashing in ESG reports, integrating explainability features for trustworthiness scores.
Full-stack and Machine Learning Development
LawSyncr, Aug 2024
- Led the end-to-end full-stack development of a Minimum Viable Product (MVP) with integrated machine learning components.
Portfolio Website Development
Arterra, Aug 2024
- Designed and developed a portfolio website, integrating CI/CD pipelines and visualizing Obsidian vault data using graphology and sigma libraries.
Crypto Trading Analysis and Future Trading
TradeBot, June 2024
- Engineered a bot to scrape trade data from Binance, enabling real-time market analysis and automated trading strategies.
Document Analysis and Optical Character Recognition (OCR)
DAVU Project TU Wien, June 2024
- Implemented an OCR pipeline using Tesseract and improved recognition performance with binarization techniques, integrated with NER for metadata extraction.
Full-stack Development of the NFT Platform
Cryptex, Feb 2024
- Implemented a secure authentication system using MetaMask and developed the backend to interact with the Polygon blockchain.
Lip Reading App at Hackathon
Coding Austria, Jul 2023
- Utilized AV-HuBERT for lip reading, enabling communication in noisy environments for the Austrian Red Cross.
2nd Place Winner
Tourism Technology Hackathon, Nov 2023
- Developed a data pipeline and knowledge graph for tourism data, visualized as an interactive map with a chatbot interface.
Studies and Publications
IEEM24-F-0298
Comparative Analysis of Machine Learning-based Surrogate Modeling Approaches for Multi-body Dynamic Simulation in Railway Digital Twin Platform, 2024
Deep Learning School
Moscow Institute of Physics and Technology, 2020 - 2021
School of Data Analysis
Higher School of Economics University and Yandex, 2020