Guidewire is building a new team to leverage its market-leading position and data access to develop advanced predictive models and variables, aiming to drive the next generation of growth in the P&C insurance market.
Requirements
- Advanced, hands on experience building modeling datasets, pipelines and features for predictive modeling
- Extensive experience using DBT, Apache Iceberg, and AWS data capabilities like Airflow, Glue, Redshift, EMR to build ML data pipelines, with a strong focus on data quality and governance.
- Expert SQL skills, including advanced functions, table design, view creation, stored procedure and script design and coding, general performance tuning
- Proficient in data processing and transformations using Apache Spark.
- Working knowledge of Python
- Experience with version control systems (e.g., Git) for managing data pipelines and features.
- Understanding of MLOps principles and practices related to data preparation and feature engineering; experience using Sagemaker and feature stores a plus
Responsibilities
- Participate in multiple simultaneous projects with a focus on data preparation and pipeline development for predictive modeling and machine learning.
- Data interrogation, exploratory data analysis, profiling, and reconciliation
- Data pipeline creation, revision and monitoring based on product manager and data scientist/actuarial input
- Feature creation, initial testing, and ongoing management
- Work collaboratively with other staff including product managers, data scientists, other data analysts, architects to solve problems, develop innovative approaches, and provide project status
- Create and manage data assets, datasets, features, and code with a focus on simplicity, scalability, reusability, and clear documentation
- Additional work assignments not related to specific project work such as new feature development, external data research, providing user feedback on new products and tools under development
Other
- Bachelors or Masters degree or equivalent industry experience
- Passion for solving complex data problems
- 7-10+ years of relevant experience
- Self-motivated and detail-oriented with desire to solve problems
- Demonstrated ability to embrace AI and apply it to your role as well as use data-driven insights to drive innovation, productivity, and continuous improvement.
