Job responsibilities

Manage end-to-end ML projects: problem definition → solution → testing → deployment → support.
Work with data engineers to build datasets and define data requirements, and assess feasibility, risks, and constraints
Work with data analysts to design and analyze A/B tests: metrics, splits, interpretation of results, and recommendations for deploying solutions.
Develop and train models (classic ML + DL), including solutions for text and image embeddings; conduct offline evaluation and error analysis.
Deploy the model and code to production (Python service), support releases and integrations.
Be responsible for model quality post-launch: metrics, monitoring, drift/degradation, improvement plans, and support procedures.

Key qualifications

4+ years of experience as a Data Scientist (with specific experience in search / ranking / recomendations tasks).
Experience managing end-to-end ML projects in production (from setup to support).
Excellent understanding of classical ML: feature engineering, boosting, classification/regression, cross-validation, threshold selection, calibration.
Experience with DL (PyTorch/TensorFlow): understanding of fine-tuning principles and model inference.
Python (production-grade): readable code, tests for critical components, understanding of model/artifact packaging and service integration.
Understanding of ML monitoring: quality metrics, drift, alerts, diagnostics, and support procedures.
SQL proficiency sufficient for independent dataset building (joins, window functions).
Experience with model interpretability and error analysis.
MLflow / W&B / DVC or similar experiment tracking tools.
Orchestration/pipelines (Airflow/Prefect/Dagster) and advanced data processing.
English at the B2 (upper-intermediate) level.