Viacheslav Zhenylenko
Verified Expert in Engineering
Machine Learning Developer
Viacheslav在数据科学和软件工程方面有8年的经验, focusing on Python, with production experience in Java and C++. 他对从原始数据中获得的见解充满热情,并喜欢将它们转化为创造卓越的商业价值. Viacheslav is well-versed in applying advanced ML techniques, such as computer vision, NLP, product recommendation systems, networking data, and classical data science to solve data-heavy projects.
Portfolio
Experience
Availability
Preferred Environment
Eclipse, Visual Studio Code (VS Code), PyCharm, Jupyter, MacOS, Linux, Vim Text Editor, Sublime Text, Bash
The most amazing...
...project I've developed was an industry-first, self-reconfigurable AutoML system for congestion detection in RAN networks.
Work Experience
Data Scientist
Creating Possibilities Limited
- Developed a parallel data collection process for hundreds of websites.
- Utilized LLMs for summarization, topic extraction, sentiment analysis, report generation, and other tasks.
- Deployed tool on AWS with Batch, EventBridge, Lambda, and others.
Data Scientist
Classic J. Vans INC.
- 开发工具,以结构化的方式从多个web源自动收集信息.
- 利用llm对原始文本进行命名实体提取和分类.
- Utilized Selenium with a proxy to emulate web clients.
- 在AWS上部署工具,包括EventBridge、ECS、Lambda、S3、QuickSight、SES等.
Data Scientist | Engineer
Spectation Sports LLC
- Developed models for MMA pre-fight prediction and in-fight forecasts.
- Utilized multiple machine learning techniques, such as boosted trees, regression, ensembling, stacking, imputation, and others.
- Performed multistep feature engineering for individual fighters.
- 从统计上确定这些数据的最有价值的特征和最佳外部来源.
- Deployed and integrated models into existing data pipelines, including elements of MLOps methodologies.
AI Engineer
Briefly
- 将OpenAI模型用于提高生产力和客户成功领域的多个任务. Performed fine-tuning, RAG, agents, function calling, and others.
- Developed distributed cloud infrastructure using Terraform, Amazon Elastic Container Service (Amazon ECS), Amazon DynamoDB, Amazon EventBridge, Amazon Simple Queue Service (SQS), AWS Lambda, and Amazon Simple Email Service (SES).
- Performed API integrations with external services and tools, including OpenAI, Google services, Slack, Notion, and Hubspot.
- Designed and built a number of Django APIs with business logic.
Senior Data Engineer
Grata Inc.
- 在Kubernetes上使用芹菜开发端到端分布式nlp地理编码管道.
- Implemented scraping from company websites and aggregators.
- 在AWS上开发并部署了SageMaker网页分类模型.
- Implemented a hybrid geocoding model with query lookup, query relaxation, result validation, prioritization, and fallback mechanisms.
- 使用可用地理数据库和离线实体提取器(如libpostal和第三方地理编码服务)的组合,将其组合在一个视图中.
- Increased a fraction of parsed addresses, reduced incorrect addresses by 95%, and improved the overall data quality score by 20%.
Lead Data Scientist
Botprise, Inc.
- 在平台上为完整的ML周期、ModelOps和MLOps开发后端. Added a wrapper on top of the AWS SageMaker.
- Worked on dozens of automation workflows (use cases), including MLOps, analytics, DataOps, networks, and ITOps.
- Created the back- and front-end elements using React for a drag-and-drop, chatbot-building application.
- Implemented and deployed dozens of algorithms (classification, clustering, time series, NLP, and computer vision) for different use cases.
- 领导一个小型机器学习团队,包括计划、管理、监控和领导.
Data Analyst
Spin (Tier Mobility)
- 使用汽车选择和汽车再培训模型,对一家全球电动滑板车租赁公司(数百个城市)的电动滑板车需求进行时间序列预测.
- Performed ad-hoc data analysis and built Looker dashboards.
- 进行干预效果分析(促销及其他活动).
Senior MLOps Engineer
Pro Football Focus, LLC
- Introduced and implemented MLOps techniques, tools, and approaches.
- Rebuilt a dozen monolithic R pipelines into distributed, modular, and functional-styled Python pipelines.
- Developed an MLOps layer on top of Dagster, Seldon, Feast, and other tools.
- Fine-tuned existing model hyperparameters both for speed and performance.
Machine Learning Engineer
Plutoshift, Inc.
- 将MLOps工具引入Seldon、Feast、Great Expectations等现有基础设施.
- Migrated existing hardcoded models to introduce the MLOps infrastructure.
- Developed back-end APIs using Django for ML-related services.
- 实现了制造传感器的分类和时间序列预测模型.
Senior AI Developer
Akcelita
- 在AWS上为来自监控摄像头的照片开发了一个摄取和处理管道.
- Experimented with various non-DL and DL approaches and tested them. 我还使用并训练了带有注意力机制的暹罗神经网络,达到了95%以上的准确率.
- 创建并与分析人员共享演示文稿,并为项目开发和维护Wiki.
Team Lead
The National Academy of Sciences of Ukraine
- Led and mentored a team of students. 我用敏捷方法定义了目标并控制了过程.
- Created a tool for crop classification and map creation.
- 手动收集数据,并通过网络抓取使用Mapillary和监督数据标签.
- 实现并测试了DeblurGAN和其他几个经典的去模糊方法.
- 通过微调ResNet模型,监督田间定位(YOLO)和作物分类.
Senior Data Scientist
Openwave Mobility
- 创建了一个多阶段的数据管道,从原始数据包数据(TCP/IP层)到机器学习模型的可消费输入,并在Python中实现多处理(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. 创建了一个可重用的Python工具,用于生成快速和外部可配置的数据分析报告.
- 实现了基于专家知识聚合的自定义特征生成算法, derivatives, TCP/IP conversation delays, products, and fractions.
- 实现了基于模型的自定义多阶段特征选择算法.
- Deployed and monitored the project in production in the network. If the tool detects congestion, optimization policies are applied. 客户报告说,视频内容的传输质量提高了20%.
Data Scientist
Octetis
- 为在线商店开发、部署并评估了一个Python混合推荐引擎.
- 监督客户行为分析、可视化和利益相关者沟通.
- Handled different scenarios of user engagement using a strategy pattern. 根据受欢迎程度(一般和基于类别)给出上下文建议。, item-to-item, and SVD. (Python, scikit-learn, SciPy).
- Integrated recommendation engine into a Django back end.
- 随机抽样进行多次A/B测试,对系统进行评估. Compared to the most popular items in the category baseline, 我们每回合的购买量提升了150%,收益也有所增加.
- 用Keras为在线云站点构造器创建了一个图像超分辨率模块.
- 利用中深度CNN,在多个模糊内核上进行训练,并通过REST将其作为服务部署.
- 进行的调查显示,该平台用户的满意度提高了约5%.
Software Engineer Intern
- 使用FBLearner Flow对AdaBoost客户流失预测模型进行培训和评估.
- Performed hyper-parameters tuning for optimization.
- Data-engineered with Hive and processed data using Python.
Research Intern
Samsung
- 开发了智能键盘功能的算法(单词预测和拼写纠正).
- 开发了n-gram的朴素贝叶斯和k -近邻(KNN)的拼写更正.
- 使用拉普拉斯平滑和自定义键盘距离为KNN创建了更好的算法性能微调.
- Developed algorithms with C++. 将它们与Java和Android键盘集成,并发布到App Store.
Software Engineer Intern
Engage Point
- Developed a Content Management Interoperability System in Jakarta EE. I used the Model-view-controller framework for the application.
- Developed Enterprise JavaBeans for the business logic of the application.
- Developed JavaServer Pages for the presentation level.
Experience
Web Scraping Mapillary
Skills
Languages
Python, SQL, Python 3, Bash, R, Snowflake, Fortran, Java, C++
Frameworks
Django, Flask, Web Frameworks, Selenium
Libraries/APIs
Scikit-learn, Keras, TensorFlow, PyTorch, Pandas, NumPy, SciPy, Beautiful Soup, Dask, Natural Language Toolkit (NLTK), Matplotlib, REST APIs, OpenCV, React Redux, PySpark, React
Tools
Jupyter, PyCharm, IPython Notebook, Amazon SageMaker, Geocoding, GIS, Vim Text Editor, Sublime Text, Plotly, Apache Airflow, Git, Celery, Jenkins, AWS CloudFormation, Grafana, Looker, Microsoft Power BI, AutoML, RabbitMQ, BigQuery, Microsoft Excel, Spreadsheets, Tableau, Notion, Android NDK, OpenAI Gym
Paradigms
Data Science, Agile Software Development, REST, Unit Testing, ETL, Parallel Programming, DevOps, Concurrent Programming, Anomaly Detection, Business Intelligence (BI), Automation, Management
Platforms
Docker, AWS Lambda, Jupyter Notebook, MacOS, Amazon Web Services (AWS), Linux, Apache Kafka, Kubernetes, Visual Studio Code (VS Code), Eclipse, Android, Java EE, Google Cloud Platform (GCP), Azure
Storage
MySQL, PostgreSQL, Data Pipelines, Data Validation, MongoDB, Elasticsearch, Datadog, Databases, Apache Hive, Cassandra, Google Cloud
Other
Predictive Analytics, Predictive Modeling, Machine Learning Automation, Computer Vision, Data Analytics, Deep Learning, Machine Learning, Mathematics, Applied Mathematics, Statistics, Algorithms, Data Analysis, Dagster, Machine Learning Operations (MLOps), Prefect, Computer Science, Web Scraping, Data Scraping, Software Development, Artificial Intelligence (AI), Programming, Computational Science, Time Series Analysis, Convolutional Neural Networks (CNN), Object Detection, Seldon, Feast, Data Visualization, Data Engineering, Analytics, Neural Networks, Software Engineering, Linear Regression, Statistical Modeling, GeoPandas, APIs, Generative Pre-trained Transformers (GPT), ChatGPT, OpenAI GPT-3 API, OpenAI GPT-4 API, OpenAI, Large Language Models (LLMs), Language Models, Recommendation Systems, Natural Language Processing (NLP), Science, Scientific Computing, DataOps, Physical Science, Networking, Physics, Applied Physics, Transformers, TCP/IP, mlpack, Explainable Artificial Intelligence (XAI), Cloud Infrastructure, Google BigQuery, API Integration, Dashboards, Quality Assurance (QA), GPT, Internet of Things (IoT), HubSpot, HubSpot CRM, LangChain, Generative Adversarial Networks (GANs), Networks, FBLearner Flow, Classification, Apache Cassandra, Sports, Software Architecture, Sentiment Analysis, DVC
Education
Master's Degree in Theoretical Physics (Quantum Field Theory)
Kyiv National University - Kyiv, Ukraine
Master's Degree in Computer Mathematics and Algebra
Kyiv National University - Kyiv, Ukraine
Bachelor's Degree in Computer Science and Applied Statistics
Kyiv National University - Kyiv, Ukraine
Certifications
AWS Machine Learning Specialty
Amazon Web Services
AWS Solutions Architect Associate
Amazon Web Services
AWS Certified Developer Associate
Amazon Web Services
Data Science: Data to Insights
MITProfessionalX DSx | edX
Artificial Intelligence (AI)
ColumbiaX CSMM.101x | edX
Second Place
ACM-ICPC, Country level
Bronze Medal
International Mathematical Olympiad (IMO)
Second Place
Kyiv International Physics Festival
How to Work with Toptal
在数小时内,而不是数周或数月,我们的网络将为您直接匹配全球行业专家.
Share your needs
Choose your talent
Start your risk-free talent trial
Top talent is in high demand.
Start hiring