Data Scientist (ML & BI) - remote from Malta

We are looking for a hands-on Data Scientist to build the machine learning models behind our next wave of products: personalization, fraud detection and CRM recommendations. You are a technical analyst at heart. You write production-quality Python and SQL, you know the ML toolbox well, and you use AI coding assistants to go from idea to working model in days, not months. Reporting directly to the Head of Data, you will own models end to end, from exploring player behaviour in Snowflake to shipping scored outputs that CRM, Risk and Product teams use every day. You will also share ownership of our Power BI reporting, so the business always has someone who can build, fix and explain a report.

- CRM & Player Lifecycle Models: Build churn, value segmentation, VIP potential and propensity models that feed CRM campaigns and VIP host portfolios. - Rapid Model Development with AI: Use AI coding assistants and modern Python tooling to prototype, test and iterate on models quickly, and to automate repetitive analysis. - Model Deployment & MLOps: Take models to production in Snowflake (Snowpark, dbtPython models) and Airflow, with versioning, scheduled retraining, monitoring and driftchecks.

- 4+ years in data science or advanced analytics, ideally in iGaming, fintech or another high-volume B2C business - Strong Python for data science and ML (pandas, scikit-learn, XGBoost/LightGBM; PyTorch or TensorFlow is a plus) - Hands-on ML experience across classification, regression, clustering, recommender systems and anomaly detection, with models taken to production

- Hands-on ML experience across classification, regression, clustering, recommender systems and anomaly detection, with models taken to production - Advanced SQL on a cloud data warehouse, preferably Snowflake; experience with dbt is a strong plus - Daily, effective use of AI coding assistants (e.g. Claude Code, Cursor, Copilot) to speed up development

- Solid grasp of statistics and experimental design (A/B testing, causal inference basics) - Experience with MLOps practices and tools (e.g. MLflow, Snowpark ML, Docker) and orchestration with Airflow is an advantage - Comfortable with Git, code review and CI/CD workflows

We are looking for a hands-on Data Scientist to build the machine learning models behind our next wave of products: personalization, fraud detection and CRM recommendations. You are a technical analyst at heart. You write production-quality Python and SQL, you know the ML toolbox well, and you use AI coding assistants to go from idea to working model in days, not months. Reporting directly to the Head of Data, you will own models end to end, from exploring player behaviour in Snowflake to shipping scored outputs that CRM, Risk and Product teams use every day. You will also share ownership of our Power BI reporting, so the business always has someone who can build, fix and explain a report. We are looking for candidates who are already based in Malta and look for a remote work set-up while living in Malta.

- Experimentation & Measurement: Design A/B tests and quasi-experimental analyses to measure the real uplift of models, promotions and product features. - Business Intelligence: Build, maintain and troubleshoot Power BI reports and semantic models, and act as cover for our BI developer so reporting never stops. - Advanced Analysis: Run deep-dive analyses on player behaviour, payments and game performance, and present clear, actionable recommendations to management.

- Daily, effective use of AI coding assistants (e.g. Claude Code, Cursor, Copilot) to speed up development - 2+ years of hands-on Power BI (DAX, Power Query, data modeling); able to own reports without supervision - Solid grasp of statistics and experimental design (A/B testing, causal inference basics)

- Rapid Model Development with AI: Use AI coding assistants and modern Python tooling to prototype, test and iterate on models quickly, and to automate repetitive analysis. - Model Deployment & MLOps: Take models to production in Snowflake (Snowpark, dbtPython models) and Airflow, with versioning, scheduled retraining, monitoring and driftchecks. - Feature Engineering: Build reusable, well-documented player features on top of ourKimball data warehouse, in close collaboration with the Data Engineering team.