ML Engineer responsibilities include both sides of the engineering and data science role. You will help our team train and deploy ML models from one side and maintain/optimize/speedup models in production from another side. You should have a strong problem-solving ability and a knack for statistical analysis.
Essential position responsibilities:
- Design and implement data pipelines that running with ML models in production;
- Maintain and optimize Python codebase for Data Science and Analytics stack;
- Be responsible for continuous and stable model operation in production with appropriate precision and recall;
- Engineering work in feature generation, code cleaning, preparation;
- Participate in code reviews;
- Monitor models performance and metrics;
- Implement integration and unit tests;
- Train ML models for different fraud types.
- Engineering background and great experience in Python and SQL;
- Click house, Docker, Kubernetes experience;
- Understanding of Unity basics;
- Solid experience with high-loaded and low-latency systems (e.g. Spark, Storm, Kafka);
- Analytical thinking and exploratory state of mind. Strong research skills;
- Deep understanding of the Machine Learning concepts and algorithms;
- Ability to process and analyze huge data volumes, ability to create and check hypothesis including data visualization;
- Degree in Computer Science, Data Science, Mathematics or similar field;
- Empathy and good communication abilities.
Would be a big plus:
- Knowledge of C#, Scala, or Go;
- Experience with deployment on the cloud;
- Experience with large-scale machine learning (100GB+ datasets);
- Experience developing and optimizing real-time software for high-loaded systems.