Data Scientist

About The Company

USAA is committed to empowering its members to achieve financial security through a comprehensive suite of highly competitive products, exceptional customer service, and trusted financial advice. With a focus on serving the military community and their families, USAA strives to be the preferred financial partner for active-duty military personnel, veterans, and their loved ones. The organization values core principles such as honesty, integrity, loyalty, and service, which guide its operations and interactions with members and employees alike. USAA also actively supports active-duty military spouses by offering remote or hybrid work opportunities, aligning with applicable policies and business needs. The company's dedication to fostering a positive and impactful work environment makes it an attractive place for professionals seeking a meaningful career in the financial services industry.

About The Role

The Lead Graph Data Scientist - Identity Analytics at USAA is a strategic and technical leadership position responsible for developing and deploying advanced quantitative solutions to detect and prevent identity theft, account takeover, and various types of fraud including synthetic fraud. This role involves designing machine learning models, deploying graph analytics capabilities, and working closely with cross-functional teams to enhance USAA’s fraud detection infrastructure. The ideal candidate will lead efforts in building and maintaining sophisticated models and graph databases, identify criminal networks, and generate actionable insights to mitigate losses and improve member experience. Additionally, this role demands mentorship of junior staff, fostering innovation through research and development, and collaborating with technology vendors and internal teams to implement enterprise-wide solutions. The position offers remote work flexibility within the continental U.S., with occasional travel, and requires a strategic thinker with a strong technical background and leadership skills.

Qualifications

• Bachelor’s degree in mathematics, computer science, statistics, economics, finance, actuarial sciences, science, engineering, or a related quantitative field; or 4 years of relevant experience in lieu of degree.
• Minimum of 8 years’ experience in predictive analytics or data analysis.
• At least 6 years’ experience in training and validating advanced analytics models including machine learning and statistical models.
• 4 years’ experience in scripting languages such as Python or R for data analysis and model development.
• Expertise in writing clean, well-documented, and transparent code.
• Strong proficiency in querying and preprocessing data from structured and unstructured databases using SQL, NoSQL, or similar query languages.
• Experience working with diverse data formats including JSON, XML, text documents, images, and delimited files.
• Proven ability to perform descriptive, diagnostic, and inferential statistics for ad-hoc analytics.
• Knowledge of regulatory considerations related to modeling and analytics efforts.
• Project management skills with a track record of managing milestones, risks, and communicating effectively about potential issues.
• Expert-level understanding of supervised learning models such as linear/logistic regression, decision trees, ensemble methods (Random Forests, XGBoost, LightGBM, CatBoost), and unsupervised techniques like clustering algorithms (k-means, hierarchical, DBSCAN).
• Experience guiding and mentoring junior data scientists and analysts.
• Excellent communication skills to convey complex technical concepts to non-technical stakeholders.
• Strong business acumen and technical expertise to collaborate effectively across organizational levels.

Responsibilities

• Develop and continuously improve internal identity theft and authentication models to mitigate fraud losses and enhance member experience.
• Partner with Strategy, Fraud Identity Analytics, Model Management, and operational teams to prioritize model development and deployment efforts.
• Collaborate with Technology and vendors to deploy graph database solutions and define enterprise fraud detection strategies.
• Implement graph analytics to identify criminal networks involved in fraud, scams, disputes, and AML activities, enhancing detection capabilities.
• Generate and prioritize fraud rings to reduce losses and improve member satisfaction.
• Integrate new data sources into models and graph solutions to increase predictive accuracy and business impact.
• Translate insights into decision systems to support fraud targeting and model refinement efforts.
• Innovate in modeling techniques, including exploring advanced methods such as graph neural networks.
• Mentor junior team members, fostering a culture of research and development within the data science team.
• Lead data analysis projects, interpreting complex data to generate actionable insights aligned with business goals.
• Manage project timelines, risks, and dependencies, escalating issues as needed to ensure successful delivery.
• Establish best practices for collaboration with Data Engineering and IT teams to deploy production-ready analytics assets.
• Stay current with industry trends, emerging techniques, and technologies in data science and fraud detection.
• Communicate technical findings to senior management and non-technical stakeholders effectively.

Benefits

• Competitive salary within the range of $164,780 - $314,960, commensurate with experience and location.
• Comprehensive health, dental, and vision insurance plans.
• Retirement plans including 401(k) with company matching.
• Paid time off and holiday benefits.
• Flexible work arrangements, including remote and hybrid options.
• Opportunities for professional development and continuous learning.
• Supportive work environment that values diversity and inclusion.

Equal Opportunity

USAA is proud to be an equal opportunity workplace and is committed to equal employment opportunity regardless of race, color, ancestry, religion, sex, national origin, sexual orientation, age, citizenship, marital status, disability, gender identity, veteran status, or any other basis protected by federal, state, or local law.