Data Scientist III***Hybrid in Alpharetta, GA

As a Data Scientist III, you will deliver moderately complex attribute-development projects in close partnership with Modelling, Technology, and internal customers. You will translate business needs into robust attribute logic, validate data and implementation quality, and support production delivery. You will also evaluate and apply artificial intelligence (AI), including machine learning and generative AI where appropriate, to improve attribute research, development, testing, and documentation. This role requires the ability to become productive quickly, exercise sound technical judgement, and work independently with minimal supervision.

Responsibilities:

• Develop and maintain KEL attributes from multiple data sources, translating business needs into analytical solutions with Modelling and Technology.

• Independently test and monitor attribute quality, completeness, and consistency using Python, ECL, Java, and other tools; diagnose defects and validate fixes.

• Maintain attribute definitions, source data documentation, business logic, validation records, user guides, and training materials.

• Partner with developers and Technology to deliver attributes into production and improve application functionality, reliability, and efficiency.

• Prototype and evaluate AI and machine learning for attribute discovery, feature engineering, and anomaly detection against established methods and defined criteria.

• Use approved generative AI and large language model (LLM) tools for coding, testing, and documentation, independently validating outputs before use.

• Apply responsible AI practices: protect sensitive data, ensure reproducibility and explainability, assess bias, document limitations, and follow governance, security, and human oversight requirements.

Clearly communicate progress, findings, risks, dependencies, and next steps to the manager and stakeholders. *

• Master’s degree in Data Analytics, Statistics, Data Engineering, Computer Science, Mathematics, or equivalent experience.

• Experience in programming, data analysis, or a related field, independently delivering moderately complex work and troubleshooting, testing, and documenting fixes.

• Experience with KEL, ECL, Python, Java, SQL, or C++, and working knowledge of relational databases, are preferred.

• Experience with analytics involving sensitive data and an understanding of privacy, security, and appropriate data handling.

• Experience in data manipulation, exploratory analysis, and validation of data quality and analytical results.

• Strong analytical, creative problem-solving, and accuracy skills, with the ability to learn and apply new tools and technologies.

• Foundational AI and machine learning knowledge, including feature engineering, training, validation, evaluation metrics, overfitting, and data leakage; understanding of LLM limitations, output validation, human review, and confidentiality.

• Practical experience with Python-based machine learning libraries or approved generative AI tools, and familiarity with responsible AI principles-explainability, fairness, reproducibility, and governance-are preferred.

Strong written and verbal communication skills, with the ability to explain technical concepts and collaborate with technical and business stakeholders.

LexisNexis Risk Solutions is an essential partner in risk assessment. Within our insurance vertical, we combine public and industry-specific content with advanced technology and analytics to help customers evaluate and predict risk and improve operational efficiency. Our insurance risk solutions help drive better data-driven decisions across the insurance policy lifecycle all while reducing risk. You can learn more about LexisNexis Risk at the link below. https://risk.lexisnexis.com/insurance