Lead Data Scientist – Compliance Analytics

This is a fully remote position, open to applicants in Alabama.

📋 Description

• Oversees and develops systems of models to evaluate a variety of large data sources.

• Leads the development, testing, and validation of models that enhance business value.

• Aids in identifying and interpreting insights derived from data.

• Provides direct leadership to the assigned data science team.

• Manages and collaborates on large data sets to address unstructured problems through diverse analytical and statistical methodologies.

• Oversees the sourcing, ingestion, and cleaning of data sets in preparation for analysis.

• Ensures data stability while accounting for complex data drift in both development and production environments.

• Manages the creation of econometric, statistical, and machine learning models for various challenges.

• Oversees the integration of complex coding into the model repository.

• Leads the selection and enhancement of models, considering performance, reliability, and stability metrics.

• Develops educational materials for model refinement and provides training for data users.

• Generates outputs from multiple models for business discussions.

• Facilitates stakeholder meetings to address concerns, opportunities, and production challenges.

• Reviews personal and assigned team’s code to ensure it is efficient, accurate, and adheres to best practices.

• Understands and complies with the Company’s risk and regulatory standards, policies, and controls.

⛳️ Requirements

• Bachelor’s degree with a minimum of 7 years of relevant experience, or alternatively, a combined total of 11 years of higher education and/or work experience, including at least 7 years of relevant experience.

• At least 2 years of managerial, supervisory, and/or leadership experience.

• Intermediate experience with various statistical methods and data science principles, including AB testing, sample selection, hypothesis testing, and modeling bias.

• Intermediate proficiency with relevant statistical software, languages, and tools.

• Experience with various hybrid databases, both on-premise and in the cloud.

• Intermediate knowledge of Structured Query Language (SQL) and Not Only Structured Query Language (nSQL).

• Expert understanding of modeling techniques, including Bayesian modeling, classification models, cluster analysis, neural networks, non-parametric methods, and multivariate statistics.

• Experience in analyzing large data sets.

🏝️ Benefits

• Medical and retirement benefits.

• Forty hours of paid volunteer time each year.