Senior Gen AI Data Scientist—RAG & Production ML

LexisNexis; Raleigh (NC); On-site; USD 105,000 - 175,000; Full time

Benefits offered by this job

Wellbeing initiatives

Shared parental leave

Study assistance

Sabbaticals

Job summary

LexisNexis is seeking a Senior Data Scientist II to advance generative AI, retrieval-augmented generation, and agentic AI systems. You will design, test, deploy, and support Python applications with emphasis on reliability, logging, and monitoring.

The role requires deep Python proficiency, experience with OpenSearch or Solr, and a track record of production-ready, cross-functional delivery. U.S. base pay ranges are provided and incentives may apply.

Qualifications

• Advanced Python proficiency demonstrated through independently designing, implementing, debugging, testing, reviewing, and refactoring production applications.
• Strong understanding of software design principles, including separation of concerns, dependency injection, interface design, and configuration management.
• Experience transforming prototype or experimental code into modular, maintainable, observable, and production-ready systems.
• Experience with distribution, observability, and reliability in production.
• Knowledge of production LLM concerns: prompts, versioning, token controls, and security.

Responsibilities

• Architect modular agentic applications with clear separation among retrieval, prompt construction, model invocation, tool execution, state management, orchestration, validation, and response formatting.
• Refactor complex Python code to improve correctness, readability, modularity, and performance.
• Own production readiness for AI components: input validation, error handling, retries, backoff, and secure credentials handling.
• Establish observability for LLM and retrieval workflows: structured logging, metrics, tracing, alerts, and error reporting.
• Design interfaces and data contracts between retrieval, orchestration, model, and downstream components.
• Write unit, integration, regression, and end-to-end tests including failure mode testing.
• Review code for correctness, maintainability, performance, security, and operational risks.
• Diagnose latency, memory usage, and retrieval performance; optimize for scalability.

Skills

Advanced Python

LLM expertise

OpenSearch/Solr

Monorepo experience

Cross-functional delivery

Production-grade systems

Tools

pytest

Mypy

Profiling tools

Job description

LexisNexis is seeking a Senior Data Scientist II to advance generative AI, retrieval-augmented generation, and agentic AI systems. You will design, test, deploy, and support Python applications with emphasis on reliability, logging, and monitoring.

The role requires deep Python proficiency, experience with OpenSearch or Solr, and a track record of production-ready, cross-functional delivery. U.S. base pay ranges are provided and incentives may apply.