Data Scientist (Mid-level) - Risk Modeling

USAA is hiring a mid-level Data Scientist for the P&C Underwriting Data Science team, focused on risk modeling and the delivery of data science products into day-to-day operations. The role combines hands-on experimentation with statistical prototyping, production deployment, and model risk management practices within the Model Development Control and Model Risk Management frameworks.

Based in San Antonio, TX, this onsite position involves turning business requests into analytical questions, building and deploying models using machine learning, simulation, and optimization, and communicating results to both technical and non-technical stakeholders.

The Opportunity

• Experiment with data, prototype statistical models, and deploy new data science products in operations for P&C Underwriting.
• Build and deploy risk and analytics models and solutions using machine learning, simulation, and optimization.

Responsibilities

• Gather, interpret, and manipulate structured and unstructured data to enable advanced analytical solutions.
• Develop scalable, automated solutions using machine learning, simulation, and optimization to deliver business insights and value.
• Select appropriate modeling techniques and/or technologies based on data limitations, the intended application, and business needs.
• Develop and deploy models within the Model Development Control (MDC) and Model Risk Management (MRM) frameworks.
• Compose technical documentation for knowledge persistence, risk management, and technical review audiences.
• Assess business needs to propose or recommend analytical and modeling projects that add business value.
• Participate in prioritization of analytics and modeling problems and research efforts with business and analytics leaders.
• Contribute to a robust library of reusable, production-quality algorithms and supporting code to support transparency and high-quality data practices.
• Translate business requests into specific analytical questions, complete analysis and/or modeling, and communicate outcomes to non-technical business partners with emphasis on actions and recommendations.
• Work with Data Engineering, IT, the business, and internal stakeholders to deploy production-ready analytical assets aligned to customer vision and specifications while meeting modeling best practices and model risk management standards.
• Maintain awareness of cutting-edge techniques.
• Actively seek opportunities and materials to learn new techniques, technologies, and methodologies.
• Ensure risks associated with business activities are effectively identified, measured, monitored, and controlled according to risk and compliance policies and procedures.

Requirements

• Bachelor's degree in Mathematics, Computer Science, Statistics, Economics, Finance, Actuarial Science, Science, Engineering, or a quantitative field; OR 4 years of relevant education and/or experience.
• 4 years of experience in predictive analytics or data analysis OR an Advanced Degree (such as a Master’s or PhD) in a quantitative discipline plus 2 years of experience in predictive analytics or data analysis.
• 2 years of experience training and validating statistical, physical, machine learning, and other advanced analytics models.
• 2 years of experience using a dynamic scripted language (such as Python or R) for statistical analyses and/or building and scoring AI/ML models.
• Experience writing code that is easy to follow, well documented, and commented where necessary for logic with high code transparency.
• Experience querying and preprocessing data from structured and/or unstructured databases using query languages such as SQL, HQL, or NoSQL.
• Experience working with structured, semi-structured, and unstructured data files such as delimited numeric data files, JSON/XML files, and/or text documents, images, etc.
• Experience conducting ad-hoc analytics using descriptive, diagnostic, and inferential statistics.
• Ability to assess regulatory implications and expectations for distinct modeling efforts.
• Experience with classical supervised modeling concepts and technologies for prediction, including linear/logistic regression, discriminant analysis, support vector machines, decision trees, and forest models.
• Experience with unsupervised modeling concepts and technologies such as k-means clustering, hierarchical/agglomerative clustering, neighbors algorithms, and DBSCAN.
• Experience communicating analytical and modeling results to non-technical business partners with emphasis on business recommendations and actionable applications of results.

Technologies

• Python, R, SQL, HQL, NoSQL
• JSON, XML
• Linear/logistic regression, discriminant analysis, support vector machines, decision trees, forest models
• K-means clustering, hierarchical/agglomerative clustering, neighbors algorithms, DBSCAN
• Machine learning, simulation, optimization, AI/ML
• Model Development Control (MDC), Model Risk Management (MRM)

Compensation

• Salary range: $114,080 - $218,030 per year.
• Pay is based on experience and market data; the actual salary may vary by location.
• Employees may be eligible for pay incentives based on overall corporate and individual performance, at the discretion of the USAA Board of Directors.

Benefits

• Comprehensive medical, dental and vision plans
• 401(k)
• Pension
• Life insurance
• Parental benefits
• Adoption assistance
• Paid time off program with paid holidays plus 16 paid volunteer hours
• Various wellness programs
• Career path planning and continuing education

Work Environment

• Flexible work environment requiring in-office presence 4 days per week.
• Position locations include San Antonio, TX; Phoenix, AZ; Plano, TX; Tampa, FL; or Colorado Springs, CO.
• Relocation assistance is not available for this position.

Additional Information

• VISA sponsorship: USAA does not provide visa sponsorship for this role.
• Applications are accepted on an ongoing basis and the posting remains open until filled.
• Equal opportunity employer.