Data Science Lead

You will

• Be a professional focal point, take part in the development and growth of our data pipeline handling massive amounts of data (calculating over a million predictions per second), guide and oversee experiments around feature engineering, model optimization, and the implementation of state-of-the-art ML tools in our pipeline.
• Solve a wide range of problems: from tabular problems using classical machine learning algorithms to implementing NLP and creating embeddings for millions of users, improving our prediction capabilities and helping leading app developers like Avito, Yandex, and Kefir acquire valuable users for their apps.
• Take part in the implementation of deep learning algorithms combining feature embeddings and accurate analysis of text descriptions of applications.
• Optimize our existing data processing pipeline together with our Java developers.
• Implement AutoML methods that automate data analysis processes.
• Research data preprocessing methods, visualizations, and monitoring experiments.

Requirements

• 3+ years of experience as a data scientist.
• Ad-Tech / mobile Marketing companies experience — Must.
• Very high-level proficiency in Python, SQL, Spark.
• Proficiency in boosted trees and XGBoost.
• Knowledge of classic ML as well as a good grasp of the mathematical logic behind it.
• Experience using ELK and AWS services (S3, Athena, SnowFlake, Aerospike, EMR, Sagemaker).
• Experience with Docker.
• Knowledge of the principles of OOP, OOAD, SOLID.
• High level of English for daily communication and conversations.