Senior Data Scientist
First seen by Alion on Sep 25, 2026.
Client
A prominent global online gambling and entertainment enterprise focused on delivering secure, compliant, and data-driven experiences for its international customer base.
Project overview
Focused on enhancing customer safety and regulatory compliance, this project involves building, evaluating, and refining predictive risk-scoring models specifically for Anti-Money Laundering (AML) and Safer Gambling (SG) risk mitigation.
Position overview
We are seeking an experienced Data Scientist to take ownership of customer risk-scoring models and exploratory risk analysis. In this role, you will analyze complex behavioral data, conduct deep-dive investigations, and construct statistical models to protect both the business and its users.
Responsibilities
Design, evaluate, and iteratively refine predictive models targeting AML and Safer Gambling risk indicators.
Conduct exploratory data analysis and targeted investigations to identify behavioral anomalies and emerging risk patterns.
Partner with compliance and operational risk teams to translate risk domain insights into practical model features.
Clearly communicate analytical methodologies, model evaluation results, and strategic insights to non-technical stakeholders.
Requirements
5+ years of professional experience in a Data Scientist role.
Strong technical proficiency in Python and SQL for complex data extraction, feature engineering, and statistical modeling.
Practical expertise in building and evaluating standard statistical and machine learning models (e.g., XGBoost, Linear/Logistic Regression).
Strong analytical problem-solving skills with a background in model evaluation metrics and data-driven investigations.
Effective verbal and written communication skills with the ability to articulate complex analytical concepts clearly.
Nice to have
Prior experience in online gaming.
Domain familiarity with Anti-Money Laundering (AML) regulations or Responsible/Safer Gambling frameworks.
Basic conceptual understanding of model deployment pipelines (hands-on engineering deployment expertise is not required).