— 3+ years of experience in software development;
— Strong knowledge of CI/CD principles;
— Experience with deploying ML models to production;
— Experience with programming in Python or Scala for Apache Spark;
— Experience with Spark ML and Python ML libs;
— Experience in test-driven development and integration testing.
— Experience with Docker;
— Experience with Apache NiFi;
— Familiar with Hortonworks or Cloudera distributions.
— Working with huge amounts of data at the largest operator in Ukraine;
— Hands on experience with Big Data technologies and tools;
— Great diversity of tasks and projects to utilize your knowledge and skills; flexibility in tools and approaches;
— Opportunity to grow within the team of talented data scientists.
— Develop ETL processes for ML pipelines;
— Automate models deployment;
— Setup and configure model quality monitoring;
— Develop automatic model refresh procedures to avoid “staleness”;
— Optimize Python/Spark code.
Within the digital transformation strategy, Kyivstar is investing resources into the development of a data management platform (DMP) based on BigData technologies, the Hadoop ecosystem and cloud computing platforms.
One of the areas of development is the elaboration and the implementation of products for internal and external customers using big data and machine learning technologies. So we are looking for a team of DataScientists — experts in the field of machine learning and analytics with practical skills in MLpipelines development using OpenSource tools.