Analyst I, Data Science

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 a Junior Data Scientist to support the work effort assessment and modeling. With guidance from senior team members, you will help build pipelines and quality checks, develop statistical and simulation models that explain and predict claim/exposure durations and action frequencies, evaluate segmentation and assignment strategies, and support work effort-based staffing forecasts and optimization.

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.

Responsibilities:

• Support development of scalable data pipelines and automated quality controls (schema, completeness, drift) across multiple sources.
• Build statistical models for duration and action frequency; build exposure/phase level features and run exploratory/variance analyses.
• Assist in clustering/segmentation and hypothesis testing to quantify efficiency and service impacts. Help build and run simulation models to compare assignment policies; analyze results and create scenario comparisons.
• Help building work effort-based demand forecasts and staffing models; implement components of optimization models with supervision.
• Maximize usable data by applying censoring aware methods, imputation, and reconciliation, document assumptions and ensure reproducibility.
• Communicate findings through dashboards, reports, and presentations; collaborate with Claims and Service partners to move insights into practice.
• Follow MLOps best practices (Git, reproducible workflows, experiment tracking) under mentorship.

Preferred skills and experience:

• Solid foundation in statistics and ML: regression/GLM, inference, experimental design; familiarity with survival/censoring, time series, and hierarchical models.
• Exposure to operations research and simulation: queueing concepts, discrete event or agent-based simulation; familiarity with OR Tools or Pyomo and SimPy is a plus.
• Proficiency in Python and SQL; experience with pandas, NumPy, scikit learn, stats models; visualization using Plotly/Seaborn and dashboarding (e.g., Dash) is a plus.
• Experience writing clean, tested code with version control (Git); familiarity with MLflow and workflow orchestration (e.g., Airflow) is a plus.
• Comfort working with large, complex operational datasets; strong problem solving, communication, and collaboration skills.

Additional skills and experiences that are nice to have:

• Coursework or experience in claims/service operations or workforce management.
• Familiarity with cloud platforms (AWS/GCP/Azure) and distributed processing (Spark).
• Exposure to Docker and CI/CD; experience deploying models or dashboards with supervision.

• Solid knowledge of predictive analytics techniques and statistical diagnostics of models.
• Advance knowledge of predictive toolset; expert resource for tool development.
• Demonstrated ability to exchange ideas and convey complex information clearly and concisely.
• Has a value-driven perspective with regard to understanding of work context and impact.
• Competencies typically acquired through a Master’s degree (scientific field of study) and 0-1 years of relevant experience or a Bachelor’s degree (scientific field of study) and 3+ years of relevant experience.