Sr Data Scientist II

Are you excited about shaping the next generation of AI-powered legal technology through generative AI, retrieval systems, and production-grade machine learning? Do you enjoy building reliable, scalable applications that transform complex AI capabilities into impactful customer solutions?

Lexis Nexis Legal & Professional, which serves customers in more than 150 countries with 11,800 employees worldwide, is part of RELX (), a global provider of information-based analytics and decision tools for professional and business customers. Our company has been a long-time leader in deploying AI and advanced technologies to the legal market to improve productivity and transform the overall business and practice of law, deploying ethical and powerful generative AI solutions with a flexible, multi-model approach that prioritizes using the best model from today’s top model creators for each individual legal use case.

The company employs over 2,000 technologists, data scientists, and experts to develop, test, and validate solutions in line with RELX Responsible AI Principles ().

We are looking for a Senior Data Scientist II with deep expertise in Generative AI, Retrieval-Augmented Generation (RAG), and agentic AI systems, combined with strong software-engineering fundamentals and demonstrated ownership of production applications. This role will focus on improving LLM-powered drafting and retrieval solutions through advanced search, embeddings, reranking, evaluation, and production-grade ML components. The successful candidate must be able to independently design, refactor, test, review, deploy, and support clean, reliable Python applications.

This includes separating agent responsibilities, designing for failure, applying sound algorithmic reasoning, and establishing appropriate logging, monitoring, testing, and operational controls. The ideal candidate has advanced Python proficiency, experience with Open Search or Solr, success working in monorepo environments, and a strong record of cross-functional delivery.

• Architect modular agentic applications with clear separation among retrieval, prompt construction, model invocation, tool execution, state and history management, orchestration, validation, and response formatting.
• Independently refactor complex or legacy Python code to improve correctness, readability, modularity, extensibility, testability, and runtime performance.
• Own production readiness for AI components, including input validation, exception handling, timeout management, retries with backoff, fallback behavior, configuration management, and secure handling of credentials.
• Establish observability for LLM and retrieval workflows through structured logging, metrics, distributed tracing, alerting, and actionable error reporting.
• Design clear interfaces and data contracts between retrieval, orchestration, model, and downstream application components.
• Write comprehensive unit, integration, regression, and end-to-end tests, including tests for failure modes, malformed model responses, empty retrieval results, and unavailable dependencies.
• Review Python and agentic application code, identify architectural and operational risks, and provide actionable feedback aligned with production engineering standards.
• Diagnose and optimize latency, memory usage, retrieval performance, token consumption, model cost, and application scalability.
• Apply appropriate data structures, algorithms, and computational-complexity analysis when designing and optimizing solutions.
• Participate in production deployments, incident investigation, root-cause analysis, remediation, and continuous reliability improvements.

• Advanced Python proficiency demonstrated through independently designing, implementing, debugging, testing, reviewing, and refactoring production applications.
• Strong command of Python fundamentals, standard data structures, common algorithms, object-oriented and functional design principles, type annotations, and time and space complexity analysis.
• Demonstrated ability to transform prototype or experimental code into modular, maintainable, observable,…