Note: The job is a remote job and is open to candidates in USA. AF Group is seeking a Principal Data Scientist with expertise in either Commercial Property or Personal Homeowners insurance to serve as an individual contributor and technical authority on applying advanced analytics and machine learning to complex business problems. This role owns the end‑to‑end analytical lifecycle, partnering closely with Actuarial, MLOps, and IT to deliver scalable solutions while ensuring long‑term model performance through rigorous validation and monitoring.
Responsibilities
- Acquires, organizes, and cleanses structured and unstructured data
- Conducts in-depth analysis to uncover trends, risks, and business opportunities
- Applies statistical modeling, machine learning, and advanced analytics to develop predictive and prescriptive solutions
- Evaluate solution performance using statistically rigorous methods and measure the impact to business outcomes
- Collaborate with MLOps and IT partners to transition solution prototypes from pilot validation into production environments
- Ensures ongoing model health through post‑deployment monitoring, drift detection, and audit‑compliant governance practices
- Creates and communicates results to senior level audiences of varying backgrounds, using business-facing presentations, reports, and dashboards
- Author and maintain comprehensive technical documentation for data lineage, codebases, results, and production changes
- Provides technical and project guidance, including peer review of work, for data science team
- Leads the evaluation of new analytic tools and processes
- Drives investigation and adoption of advanced machine learning and AI innovations
Skills
- Bachelor's Degree in Data Science, Statistics, Mathematics, Operations Research, Actuarial Science, Computer Science, Engineering, Physics or related technical field required
- 10 years of experience in data science or related advanced analytics domains, including research and teaching, with 3+ years of technical leadership
- 3+ years of experience supporting underwriting functions, including loss modeling, for Commercial Property (preferred) or Personal Homeowners insurance
- Demonstrated expertise using Poisson, Gamma, and Tweedie distributions to build loss ratio, pure premium, and frequency–severity loss models for pricing
- Extensive experience leveraging supervised learning models (e.g., XGBoost, GLM, etc.) and unsupervised techniques (e.g., K-means, PCA, etc.) to solve complex data science problems
- Advanced Python programming skills supporting data science, including scikit-learn and pandas
- Proficient data wrangling and ETL abilities using SQL on relational databases
- Comfortable explaining machine learning models with partial dependence plots and SHAP values
- Ability to conduct experiments e.g., A/B Testing, to evaluate the causal impact of model-driven decisions
- Experience using version control tools such as Git and Azure DevOps
- Experience working in cloud computing environments such as Azure, AWS, GCP, etc
- Experience supporting at least one other commercial or personal line outside of Property lines
- In-depth understanding of General Liability (aka Casualty), Workers Compensation, or Commercial Vehicle insurance
- Knowledge of actuarial concepts and terminology used in pricing and ratemaking
- Experience with Claims, Marketing, or Operations functions within P&C insurance settings
- Ability to develop Agentic AI solutions to drive autonomous decision‑making and task orchestration
- Familiarity with causal modeling techniques such as Meta-learners, Causal Forest, Double ML, etc
- Knowledge of advanced neural net architectures like LSTM, CNN, Transformers, Graph NN, etc
- Understanding of NLP concepts such as topic modeling, Word2Vec, sentiment analysis, OCR, etc
- Experience programming in the R language
- Ability to build interactive dashboards using frameworks such as Plotly Dash, Power BI, Flask, etc
Company Overview