Sr Data Scientist

Quick Facts

• Central focus: Data science and machine learning for security, trust & safety, and risk detection (e.g., cheating, fraud, account abuse, botting)

Description

Lead end-to-end data science initiatives, from problem definition and exploratory analysis through model development, evaluation, deployment, and monitoring. Design and develop statistical and machine learning models to detect cheating, fraud, account abuse, botting, suspicious gameplay, and other emerging platform risks. Build scalable features, risk signals, and detection frameworks using gameplay telemetry, player behavior, account, transaction, and operational data.

Investigate complex abuse patterns, translate insights into models, rules, dashboards, and recommendations, and continuously improve detection quality by optimizing model performance and reducing false positives. Establish best practices for model evaluation, monitoring, drift detection, and impact measurement while partnering with engineering teams to productionize data science solutions. Collaborate with product, security, anti-cheat, fraud, game, and operations teams to develop data-driven prevention and enforcement strategies.

Mentor junior data scientists, promote reusable data science practices, and communicate analytical findings, model tradeoffs, and business impact to technical and non-technical stakeholders.

Responsibilities

• Lead end-to-end data science initiatives (problem definition → exploration → modeling → evaluation → deployment → monitoring)
• Design and develop statistical and machine learning models for cheating, fraud, account abuse, botting, suspicious gameplay, and emerging risks
• Build scalable features, risk signals, and detection frameworks using gameplay telemetry and multi-source player/account/transaction/operational data
• Investigate complex abuse patterns; convert insights into models, rules, dashboards, and recommendations
• Continuously improve detection quality by optimizing model performance and reducing false positives
• Establish best practices for evaluation, monitoring, drift detection, and impact measurement; partner to productionize solutions
• Collaborate cross-functionally across product, security, anti-cheat, fraud, game, and operations
• Mentor junior data scientists and communicate findings, tradeoffs, and business impact

Requirements

• 7+ years of experience in Data Science, Machine Learning, Applied Statistics, Fraud Detection, Security Analytics, Trust & Safety, or a related analytical field
• Strong proficiency in Python or R and advanced SQL
• Experience leading end-to-end machine learning projects from ambiguous problem definition through production deployment
• Expertise building statistical or machine learning models using large-scale behavioral, transactional, telemetry, account, or security datasets
• Strong understanding of model evaluation (precision/recall tradeoffs, threshold optimization, calibration, false positives, monitoring, performance measurement)
• Experience engineering features from complex, multi-source datasets and translating business or security problems into scalable analytical solutions
• Proven ability to partner cross-functionally with engineering, product, security, fraud, or operations teams to deliver production-ready models, dashboards, and decision-support tools
• Experience mentoring technical teammates and communicating complex analytical insights to diverse audiences

Preferred Qualifications

• Experience in gaming, anti-cheat, trust & safety, fraud prevention, cybersecurity, account abuse, bot detection, or other adversarial environments
• Experience developing detection frameworks, risk scoring models, anomaly detection, graph analytics, clustering, sequence modeling, or human-in-the-loop review systems
• Familiarity with gameplay telemetry, player behavior analytics, account lifecycle data, commerce systems, or live-service game operations
• Experience operationalizing ML solutions with cloud and data platforms such as AWS, GCP, Spark, Databricks, Snowflake, Kafka, Airflow, or Kubernetes
• Experience balancing detection effectiveness with player experience, operational efficiency, and business impact in rapidly evolving threat environments

Benefits

• Vacation: 3 weeks per year to start
• Sick time: 10 days per year
• Paid top-up to EI/QPIP benefits up to 100% of base salary when welcoming a new child (12 weeks maternity, 4 weeks parental/adoption)
• Extended health/dental/vision coverage
• Life insurance
• Disability insurance
• Retirement plan to regular full-time employees
• Certain roles may be eligible for bonus and other incentive programs