Senior Predictive Liability Analytics Lead

Corebridge Financial • Los Angeles, CA

1d • $190,000 - $210,000 • Hybrid

About The Position

Join Corebridge Financial's Balance Sheet Risk Management (BSRM) group as a hands-on Senior Predictive Liability Analytics Lead. This technical leadership role focuses on building next-generation short-term models of policyholder behavior, initially concentrating on annuity surrenders, withdrawals, and utilization. You will collaborate with various stakeholders including financial planning, ALM, pricing, valuation, and capital teams. While not a people management or strategy role, you will be responsible for the technical execution, including mathematical modeling and coding, and will mentor others through your example.

Requirements

• Master’s/PhD in Statistics, Data Science/ML, Applied Math, Computer Science, or Actuarial Science; FSA/ASA a plus (or equivalent domain depth).
• 7+ years building production predictive models; insurance/annuity or long-duration liability exposure preferred.
• Practical experience in behavior modeling (surrender/utilization/lapse) and integration with projection engines.
• Comfortable spanning structured + unstructured data and bridging to projection engines.
• Clear, concise communicator with strong documentation habits and a bias to ship and iterate.
• Python (pandas, NumPy, scikit-learn, XGBoost/LightGBM, PyTorch/TensorFlow), SQL.
• Experience with NLP/LLM: transformers/embeddings, RAG, prompt engineering; genetic/evolutionary search for features/hyper-params.
• Experience with Databricks/Spark, Snowflake, AWS/Azure; MLflow, model registries, CI/CD; Tableau/Power BI for monitoring & storytelling.
• Working familiarity with Actuarial platform (AXIS/Prophet/RAFM/etc.) integration patterns (assumption tables, mapping layers).

Nice To Haves

• Certifications in ML/AI.

Responsibilities

• Design predictive and semi-structural models with a short-term focus (18-36 months) on long-horizon behavior (surrenders, partial withdrawals, lapse, rider utilization) using various statistical and machine learning techniques (GLMs/GAMs, survival & hazard models, tree ensembles, deep learning).
• Leverage unstructured data (contract text, correspondence, customer notes, call transcripts) using NLP/transformer embeddings, RAG pipelines, and LLM-assisted document parsing to create novel behavioral features.
• Pilot generative-AI for feature extraction/summarization and use genetic/evolutionary algorithms for feature selection, architecture search, or synthetic cohort generation.
• Develop scenario-aware models incorporating drivers like credited rate, market rate spreads, moneyness, surrender charge state, and distribution channel effects, calibrating elasticity to economic conditions.
• Translate model outputs into consumable curves/driver functions for projection engines (e.g., Moody’s AXIS, Aon Pathwise, Prophet, RAFM, or internal models), ensuring reproducible and versioned results.
• Share models with valuation/projection/ALM teams to integrate behavior sensitivities into cash-flow projections, LDTI assumption updates, RBC/CTE stresses, and hedge effectiveness studies.
• Partner with valuation and pricing teams to reconcile actual vs. expected results and attribute earnings/variance to behavior, documenting the model story and explainability for governance.
• Build training/scoring pipelines in Python/SQL on platforms like Databricks/Spark/Snowflake/AWS, tracking experiments with MLflow/DVC, versioning in Git, packaging with containers, and serving via batch/API.
• Establish dashboards for calibration, drift, stability, and bias monitoring, setting retraining schedules, fallback models, rollback criteria, and automated alerts.
• Co-design experiments (A/B, uplift, causal inference) with Business Owners/Operations/Distribution to test interventions, exploring contextual bandits/RL for offer timing and messaging when appropriate.
• Support Actuarial/Finance/Capital teams on scenario stress, attribution, and sensitivity runs, including presenting results to model governance, assumption committees, and internal validation.
• Mentor by example, setting standards for code quality, reproducibility, and testing.
• Balance accuracy, interpretability, and operational simplicity under governance.
• Collaborate within a highly matrixed organization.

Benefits

• Medical insurance
• Dental insurance
• Vision insurance
• Mental health support
• Wellness initiatives
• 401(k) Plan with generous dollar-for-dollar Company matching contribution up to 6% of eligible pay and a Company contribution equal to 3% of eligible pay (US)
• Employee Assistance Program (confidential counseling services and resources)
• Matching charitable donations (1:1 up to $5,000)
• Volunteer Time Off (up to 16 hours annually)
• Paid Time Off (at least 24 days)

What This Job Offers

• Job Type: Full-time
• Career Level: Senior