Staff Data Scientist / Machine Learning Engineer

This is a fully remote position, open to applicants in Poland, +5 more countries.

📋 Description

• Design, construct, and sustain predictive Lifetime Value (pLTV) models employing XGBoost, CatBoost, and probabilistic forecasting techniques.

• Develop and oversee a tiered scoring system that allocates users to prediction models based on the availability of data and the quality of signals.

• Create and refine calibration frameworks that transform raw model outputs into values suitable for business applications.

• Take ownership of feature engineering processes and manage scalable feature datasets derived from transactional, behavioral, and engagement data.

• Establish and uphold feature quality standards to ensure reliable inputs for production models.

• Monitor model performance, drift, and shifts in data distribution; identify when retraining or adjustments to the model are necessary.

• Evaluate the impact of deployed models on downstream outcomes and identify feedback loops that may influence model accuracy.

• Enhance identity resolution across various behavioral and transactional data sources.

• Construct, test, and maintain production-grade Python services and data pipelines for model training, scoring, and signal delivery.

• Implement automated testing, CI/CD processes, monitoring, idempotent processing, and deployment safeguards.

• Collaborate with data, engineering, and product stakeholders to address data quality, model effectiveness, and scalability of the platform.

• Operate and optimize machine learning workflows in cloud environments using orchestration, scheduling, and distributed processing tools.

• Ensure the reliability, accuracy, and scalability of machine learning systems that support business decision-making and performance enhancement.

⛳️ Requirements

• A minimum of 5 years of practical experience in ML engineering using Python, with production-deployed models.

• Proficient in production-grade Python coding, extending beyond prototypes or Jupyter notebooks.

• Experience with gradient boosted trees, including XGBoost, CatBoost, or LightGBM, with skills in hyperparameter tuning, feature importance analysis, and model evaluation beyond standard metrics.

• Strong proficiency in SQL and BigQuery, including complex feature engineering queries, scheduled transformations, and data validation logic.

• Practical experience with Google Cloud Platform (GCP), encompassing Cloud Run, Airflow/Composer, Vertex AI, and Pub/Sub.

• Understanding of model calibration and the correlation between prediction errors and downstream optimization systems.

• Experience integrating outbound APIs to transmit model outputs to external systems.

• Preferred experience in the e-commerce or direct-to-consumer (DTC) domain.

• Familiarity with probabilistic customer models such as BG/NBD or Gamma-Gamma is preferred.

• Preferred experience in ad platform signal engineering, including Google Ads API or Meta Conversions API.

• Preferred experience in identity resolution or entity matching.

• Experience with Terraform, CI/CD pipeline design, and Docker containerization is a plus.

• Familiarity with causal inference, A/B testing in advertising spending environments, or multi-armed bandit allocation is a plus.

• Familiarity with agentic development workflows such as Claude Code or Cursor is a plus.

🏝️ Benefits

• Competitive salary and performance-based bonuses.

• Comprehensive health benefits including medical, dental, and vision coverage.

• Flexible work hours and remote work options.

• Opportunities for professional development and career advancement.

• Supportive and innovative work environment.