Data Scientist

Responsibilities:

• Design, train, and deploy supervised ML models to predict purchase propensity, churn, and re-engagement opportunities, and build player segmentation and behavioral models.
• Develop personalized offer recommendation and ranking systems for in-game store personalization.
• Build feature engineering pipelines from large-scale player datasets (gameplay behavior, economy data, IAPs, progression, LiveOps, engagement, and analytics events).
• Design and run A/B experiments to measure uplift in revenue/engagement and evaluate recommendation quality post-deployment.
• Deploy models as production-ready inference APIs/pipelines, monitor model drift, retrain on fresh data, and collaborate with backend engineers on integration.

Requirements:

• 3+ years of experience in machine learning/data science roles.
• Strong understanding of supervised learning, classification and regression models, feature engineering, model evaluation, cross-validation, and hyperparameter tuning.
• Must have experience with XGBoost, LightGBM, CatBoost, scikit-learn, pandas/Polars, and NumPy.
• Programming proficiency in Python, advanced SQL, and Git.
• Experience working with BigQuery or Snowflake, large behavioral datasets, event-based analytics, data preprocessing, and feature engineering.

Good to Have:

• Recommendation Systems, Ranking Models, Collaborative Filtering, and Sequential Recommendation Models.
• Reinforcement Learning / Contextual Bandits, Feature Stores, MLflow, Vertex AI, Airflow, Docker, Kubernetes, FastAPI. Experience with modern AI tools such as LLM APIs, AI agents, prompt engineering, RAG, MCP, and tool-calling workflows (while this role primarily focuses on classical ML, familiarity with modern AI systems is highly desirable).