Senior ML Engineer

Art of Spin is seeking a Senior ML Engineer to design and implement a full machine learning production stack for player retention scoring. The role focuses on building reliable infrastructure with reproducible feature pipelines, stable model training, scalable batch inference, and monitoring systems that ensure models remain trustworthy over time.

• Build and maintain leakage-safe, time-based feature pipelines for behavioral player data
• Ensure strict feature parity between training and inference environments
• Productionize tabular ML models (CatBoost, XGBoost) for churn and retention scoring
• Package training and inference pipelines into reliable, modular services
• Version datasets, features, and models to guarantee reproducibility
• Implement monitoring for data quality issues, drift, and model performance decay
• Design cost-efficient cloud infrastructure using Docker-first architecture
• Build alerting, debugging workflows, and operational documentation for the ML platform

• 4+ years of experience in ML Engineering / MLOps with production systems
• Expert-level Python and strong SQL skills
• Hands-on experience deploying tabular ML models (CatBoost, XGBoost or similar)
• Strong understanding of time-based feature engineering and leakage prevention
• Experience building reproducible ML pipelines and model versioning systems
• Experience with Docker and scalable inference services
• Engineering mindset: production-grade code, testing, and observability
• Plus: Experience in gaming, sportsbook, casino, payments, risk, or fraud systems; ClickHouse, Kafka, or Spark; SHAP or explainability tools; dbt or analytics engineering workflows

Tech Stack: Python, SQL, CatBoost, XGBoost, FastAPI, Docker, Kubernetes, MLflow, Airflow/Prefect/Dagster, AWS (EC2, EKS, S3), GitHub Actions/GitLab CI

Benefits: Full ownership of greenfield ML platform, direct impact on revenue-driving retention systems, high autonomy in technical decisions, competitive compensation, flexible working format, opportunity to shape ML engineering foundation