The Insider Risk team and Information Security Data Operations team are centralizing Insider Risk data in the Cybersecurity Data Lakehouse. This Data Scientist will work with developers and data analysts to build risk and quantitative models around Insider Risk data — ultimately creating a human risk score for the Insider Risk program. The role is responsible for designing, building, and continuously improving quantitative models, statistical methods, and analytical frameworks used to identify, assess, and prioritize insider risk across employees, contractors, vendors, and non-human identities.
- Design and build quantitative risk models, statistical methods, and scoring frameworks for insider threat detection.
- Develop, validate, and continuously improve ML models including regression, classification, anomaly detection, and clustering.
- Build the human risk score that underpins the Insider Risk program.
- Work with complex enterprise datasets across identity, endpoint telemetry, DLP, email, and collaboration platforms.
- Translate analytics findings into defensible risk signals, scoring models, and executive-level metrics.
- Support centralization of Insider Risk data in the Cybersecurity Data Lakehouse.
- Ensure model explainability, governance, and validation meet standards for regulated environments.
- Support investigations, governance forums, and regulatory scrutiny with transparent scoring logic.
- Apply behavioral analytics and employee lifecycle risk frameworks.
- Communicate complex analytical concepts clearly to non-technical stakeholders across Cyber, HR, Legal, and Compliance.
- Collaborate with program partners to align risk models with investigation and governance needs.
Bachelor's or Master's degree in Data Science, Statistics, Applied Mathematics, Economics, Quantitative Finance, Computer Science, or related discipline.
5+ years of experience in data science, quantitative analysis, or risk modeling, preferably in financial services or regulated industries.
Strong experience building statistical or machine learning models — regression, classification, anomaly detection, and clustering.
Proficiency in Python and/or R, with experience in SQL for large-scale data analysis.
Hands-on experience working with complex enterprise datasets and translating analytics into business decisions.
Strong communication skills with the ability to explain complex analytical concepts to non-technical stakeholders.
Experience supporting Insider Risk, Fraud, AML, Cybersecurity, UEBA, or Threat Analytics programs.
Familiarity with identity and access data, endpoint telemetry, DLP, email, or collaboration monitoring.
Experience with model explainability, governance, and validation in regulated environments.
Knowledge of employee lifecycle risk, behavioral analytics, or human-centric risk modeling.