Assistant Director, Data Science, Capacity Modeling

Description

At Liberty Mutual, the Capacity Modeling and Optimization team within Claims and Service Data Science builds advanced forecasting and staffing optimization models that enable best in class workforce planning across our Claims and Service lines of business. We convert operational data into decision grade analytics that improve assignment strategies, benchmark productivity, and align capacity with demand.

We are hiring an Assistant Director, Data Science to lead work effort assessment and modeling. You will use advanced statistics, simulation, and optimization to quantify how adjusters work, identify segmentation opportunities, and recommend policy changes that increase efficiency and improve outcomes. You will partner closely with Operations and Workforce Management to bring models into production and measure impact.

This role may have in office requirements based on candidate location. Level of position offered will be based on skills and experience at manager discretion.

• Apply advanced analytics to step/click level and other operational data to model claim/exposure durations and action frequencies; build stochastic models that capture variability and drivers.
• Develop clustering/segmentation strategies for claims and exposures; design statistically rigorous tests to evaluate efficiency gains and service impacts.
• Build simulation models to compare assignment policies; quantify throughput, cycle time, and quality tradeoffs; create the mathematical case for recommendations.
• Create work effort-based demand forecasts and staffing models; solve allocation and scheduling problems using mathematical optimization; deliver scenario analyses for planners.
• Build and maintain data pipelines and automated quality checks; maximize usable data via censoring aware methods, imputation, and reconciliation across sources.
• Follow MLOps best practices to produce reproducible code, versioned experiments, and monitored models; collaborate with engineering to operationalize datasets, dashboards, and services.
• Provide technical mentorship, communicate findings to diverse stakeholders, and contribute to cross functional initiatives and best practices

• Broad knowledge of predictive analytic techniques and statistical diagnostics of models.
• Expert knowledge of predictive toolset; reflects as expert resource for tool development.
• Demonstrated ability to exchange ideas and convey complex information clearly and concisely.
• Networks with key contacts outside own area of expertise. Ability to establish and build relationships within the aligned functional area or SBU.
• Ability to give effective training and presentations to peers, management and less senior business leaders.
• Ability to use results of analysis to persuade team or department management to a particular course of action.
• Has a value driven perspective with regard to understanding of work context and impact.
• Competencies typically acquired through a Ph.D. degree (in Statistics, Mathematics, Economics, Actuarial Science or other scientific field of study) and a minimum of 2 years of relevant experience, a Masters degree (scientific field of study) and a minimum of 4 years of relevant experience or may be acquired through a Bachelors degree(scientific field of study) and a minimum of 5+ years of relevant experience.

• Strong foundation in statistical modeling and inference, including hierarchical/Bayesian methods, survival/censoring analysis, GLM/GAM, time series forecasting, and experimental design/causal inference.
• Expertise in operations research and simulation: discrete event or agent-based simulation, queueing theory, and optimization (linear/mixed integer programming).
• Proficiency in Python and SQL; experience with data manipulation and modeling libraries (pandas, NumPy, scikit learn, statsmodels; PyMC a plus) and OR tools (Pyomo or OR Tools); familiarity with SimPy or similar simulation frameworks.
• Experience building production data pipelines and applying MLOps practices (Git, CI/CD, experiment tracking such as MLflow) and workflow orchestration (e.g., Airflow).
• Ability to translate analytics into operational recommendations and influence decision making in partnership with Claims, Service, and Workforce Management.
• Track record of moving models from prototype to production and measuring impact through experiments or counterfactual analysis.

• Knowledge of claims and service operations, exposure level modeling, and workforce management practices.
• Experience with cloud platforms (AWS preferred), distributed data processing (Spark), and dashboarding/visualization tools.
• Familiarity with reinforcement learning or bandit methods for dynamic routing or assignment.

• California
• Los Angeles Incorporated
• Los Angeles Unincorporated
• Philadelphia
• San Francisco