Viacheslav Zhenylenko, Machine Learning Developer in Kiev, Ukraine
Viacheslav Zhenylenko

Machine Learning Developer in Kiev, Ukraine

Member since April 29, 2019
Viacheslav has five years of experience in data science and software engineering. He is passionate about the insights gained from raw data and enjoys converting it to create exceptional business value. His primary expertise is Python, with production experience in Java and C++. He has applied advanced machine learning techniques such as Computer Vision, NLP, Product Recommendation Systems, networking data, and classical data science problems.
Viacheslav is now available for hire

Portfolio

Experience

Location

Kiev, Ukraine

Availability

Full-time

Preferred Environment

Linux, macOS, Jupyter, PyCharm, VSCode, Eclipse.

The most amazing...

...project I've developed is an industry first; a self-reconfigurable AutoML system for congestion detection in RAN networks.

Employment

  • Team Lead

    2018 - 2019
    The National Academy of Sciences of Ukraine
    • Led and mentored a team of students. I defined objectives, and controlled the process using the Agile methodology.
    • Created a tool for crops classification and map creation.
    • Collected data both manually, and via web scraping using Mapillary, and oversaw the data labeling.
    • Implemented and tested DeblurGAN, as well as several other classic deblurring methods.
    • Oversaw field localization (YOLO), and crop classification by fine-tuning a ResNet model.
    Technologies: Python, Keras, TensorFlow, PyTorch, OpenCV
  • Senior Data Scientist

    2017 - 2019
    Openwave Mobility
    • Created a multi-staged data pipeline from raw packets data (TCP/IP layer) to consumable inputs for machine learning models with multi-processing implementation in Python (CPython).
    • Trained, tuned, evaluated and compared multiple machine learning models in Python (scikit-learn, Keras, XGBoost, CatBoost) and C++ (mlpack).
    • Oversaw the data analysis and communication with stakeholders. Created a reusable Python tool for rapid and externally configurable data analysis reports generation.
    • Implemented custom feature generation algorithms based on expert knowledge based on aggregation, derivatives, delays in TCP/IP conversation, products, and fractions.
    • Implemented custom multi-staged feature selection algorithms that were model based.
    • Deployed and monitored the project in production in the network. If the tool detects congestion, optimization policies were applied. Customers reported up to a 20% increase of quality of delivery for video content.
    Technologies: Python, C++
  • Data Scientist

    2015 - 2017
    Octetis
    • Developed, deployed, and evaluated a hybrid recommendation engine in Python for an online store.
    • Oversaw customer behavior analysis, visualization, and stakeholder communication.
    • Handled different scenarios of user engagement using a strategy pattern. Contextual recommendations were given based on popularity (general and category-based), item-to-item, and SVD. (Python, scikit-learn, SciPy). The system was integrated into a Django website.
    • Conducted multiple A/B tests with random sampling for evaluation of the system. Compared to the most popular items in the category baseline, we achieved up to a 150% boost in purchases-per-session, and increase of revenue.
    • Created an image super-resolution module for an online Cloud site constructor with Keras.
    • Utilized middle-deep CNN, trained on several blur kernels, and deployed it as a service via REST.
    • Conducted surveys showing an increase of about 5% in the satisfaction for users of the platform.
    Technologies: Python, Keras, TensorFlow
  • Software Engineer Intern

    2015 - 2015
    Facebook
    • Trained and evaluated AdaBoost models for customer churn prediction using FBLearner Flow.
    • Performed hyperparameters tuning.
    • Data engineered with Hive, and processed data using Python.
    Technologies: Python, Hive
  • Researcher Intern

    2014 - 2015
    Samsung
    • Developed algorithms for smart keyboard functionality (word prediction and spelling correction).
    • Developed Naive Bayes for n-grams, and K-Nearest Neighbors (KNN) for spelling corrections.
    • Created tweaks for better algorithm performance using Laplace smoothing, and a custom keyboard distance for KNN.
    • Developed algorithms with C++. Integrated them with a Java to Android keyboard and published to the AppStore.
    Technologies: Java, Android, C++
  • Software Engineer Intern

    2013 - 2014
    Engage Point
    • Developed a Content Management Interoperability System in Java EE. I used the Model View Controller framework for the application.
    • Developed Enterprise Java Beans for the business logic of the application.
    • Developed JavaServer Pages for the presentation level.
    Technologies: Java EE

Skills

  • Languages

    Python, SQL, Java, C++, R
  • Other

    Machine Learning, Deep Learning
  • Libraries/APIs

    Sklearn, Keras, TensorFlow, Pandas, NumPy, PyTorch
  • Tools

    IPython Notebook, Git
  • Paradigms

    Agile Software Development
  • Platforms

    Linux
  • Storage

    MySQL
  • Frameworks

    Django

Education

  • Master's degree in Mathemetics
    2018 - 2020
    Taras Shevchenko National University of Kiev - Kiev, Ukraine
  • Bachelor's degree in Computer Science and Applied Statistics
    2010 - 2014
    Taras Shevchenko National University of Kiev - Kiev, Ukraine

Certifications

  • Data Science: Data to Insights
    MAY 2017 - PRESENT
    Massachusetts Institute of Technology (MITx)
  • CSMM.101x: Artificial Intelligence (AI)
    JANUARY 2017 - PRESENT
    ColumbiaX
  • 2nd Place
    MAY 2011 - PRESENT
    ACM-ICPC, Country level
  • Bronze Medal
    JULY 2010 - PRESENT
    International Mathematical Olympiad (IMO)
  • 2nd Place
    MAY 2009 - PRESENT
    Kyiv International Physics Festival

To view more profiles

Join Toptal
Share it with others