Senior AI Systems Engineer — LLM & RAG

LexisNexis Risk Solutions; Oklahoma City (OK); Hybrid; USD 95,000 - 159,000; Full time

Benefits offered by this job

401(k) with match

Employee Share Purchase Plan

Wellbeing resources

Disability and life insurance

Family benefits

Health Savings Accounts

Paid time off and volunteering

Job summary

LexisNexis Risk Solutions is seeking an experienced AI software engineer to design and deploy production AI systems, including agentic workflows and RAG-powered pipelines. You will translate unstructured problems into measurable AI solutions, mentor junior engineers, and collaborate with business users to define requirements.

The role emphasizes end-to-end ownership of AI features, evaluation frameworks, and cost-aware LLM deployments across AWS and Azure, with a strong focus on structured

Qualifications

• 5+ years of software engineering experience, including 2+ years building and shipping LLM-based or ML-based systems to production.
• BS in Engineering/Computer Science or equivalent experience required.
• Demonstrated track record of owning an AI feature or service end to end: design, evaluation, deployment, and monitoring.
• Expert proficiency in TypeScript/Node.js and/or Python; working knowledge of C#/.NET is a plus.
• Hands-on experience with LLM platforms and APIs (Azure OpenAI or equivalent), including prompt design, tool/function calling, structured outputs, and model selection tradeoffs.
• Experience building RAG pipelines: chunking, embedding, hybrid retrieval, reranking, and grounding/citation.
• Strong understanding of schema-driven structured extraction from unstructured data (Zod, Pydantic, JSON Schema) and validation strategies.
• Experience with evaluation frameworks for AI systems: golden datasets, LLM-as-judge, precision/recall on extraction tasks, regression testing of prompts and agents.
• Strong SQL proficiency and understanding of relational and vector data storage (SQL Server, PostgreSQL, Elasticsearch/vector stores).
• Working experience with both AWS and Azure, including compute, storage, networking, IAM, and managed AI services; containerized deployment (Docker, Kubernetes or equivalent), secrets management, and observability (token usage, latency, cost attribution).
• Strong knowledge of software development best practices, test-driven development, and code review.

Responsibilities

• Design, build, and deploy production AI systems including agentic workflows, RAG services, and extraction pipelines across multiple business units.
• Interface with business stakeholders and technical team members to scope AI use cases, define success metrics, and finalize requirements.
• Write and review detailed technical specifications and architecture documents for complex AI system components.
• Build and maintain evaluation harnesses; establish accuracy, latency, and cost baselines and monitor them in production.
• Implement responsible AI practices: data handling, PII controls, hallucination mitigation, auditability, and human review where required.
• Own cost and performance of LLM workloads, including model selection, caching, and usage attribution.
• Build and maintain CI/CD pipelines and deployment automation for AI services across AWS and Azure environments.
• Operate in Agile development environments while collaborating with key stakeholders across engineering, product, and business functions.
• Mentor less-senior engineers on AI system design, evaluation methodology, and production readiness.

Skills

TypeScript/Node.js

Python

C#/.NET

LLM platforms

SQL

AWS

Azure

Docker/Kubernetes

Structured extraction

Schema validation

Education

BS in Engineering/Computer Science

Tools

Azure OpenAI

SQL Server

PostgreSQL

Elasticsearch

Docker

Kubernetes

CI/CD

Job description

LexisNexis Risk Solutions is seeking an experienced AI software engineer to design and deploy production AI systems, including agentic workflows and RAG-powered pipelines. You will translate unstructured problems into measurable AI solutions, mentor junior engineers, and collaborate with business users to define requirements.

The role emphasizes end-to-end ownership of AI features, evaluation frameworks, and cost-aware LLM deployments across AWS and Azure, with a strong focus on structured