Sr AI Engineer (RAG, Python)

Salary: $104,900 - 174,700 per year Requirements:

• We need proven experience as an AI Engineer or in a closely related position.
• We need strong Python programming expertise.
• We need deep knowledge of Retrieval-Augmented Generation (RAG) models.
• We need proven prompt engineering experience.
• We need experience with machine learning frameworks and libraries such as TensorFlow or PyTorch.
• We need proficiency in data preprocessing and feature engineering techniques.
• We need hands-on experience building agentic AI applications, including tool or function calling, multi-agent orchestration, and autonomous workflow design.
• We need demonstrated experience using AWS cloud services such as SageMaker, Bedrock, Lambda, EC2, and S3 to build and deploy AI or ML solutions.
• We need excellent problem-solving skills and a strong attention to detail.
• We need strong communication and teamwork abilities.
• Preferred: experience with cloud platforms, especially AWS; familiarity with Azure or Google Cloud is a plus.
• Preferred: experience with agentic AI frameworks and tools such as LangGraph, LangChain, AutoGen, CrewAI, AWS Bedrock Agents, or Model Context Protocol.
• Preferred: AWS certification such as AWS Certified Machine Learning - Specialty or AWS Certified Solutions Architect.
• Preferred: knowledge of natural language processing (NLP) techniques.
• Preferred: familiarity with version control systems such as Git.
• Preferred: experience deploying AI models in production environments.

• We test, evaluate, and implement AI models with a focus on Retrieval-Augmented Generation (RAG).
• We apply strong prompt engineering and prompt testing to achieve the desired outcomes.
• We collaborate with cross-functional teams to integrate AI solutions into existing systems.
• We optimize and fine-tune RAG models for performance, scalability, and cost efficiency.
• We conduct research and stay current on the latest advances in AI and machine learning.
• We design, build, and deploy agentic AI systems that can plan autonomously, use tools, and complete multi-step tasks using frameworks such as LangGraph, AutoGen, or CrewAI.
• We architect and deploy AI/ML and RAG solutions on AWS using services such as SageMaker, Bedrock, Lambda, and S3.
• We write clean, efficient, and maintainable Python code.
• We perform data preprocessing, feature engineering, and model evaluation.
• We troubleshoot and debug AI models and applications in a monorepo environment.
• We document AI models, processes, and workflows.

• AI
• AWS
• Lambda
• Architect
• Azure
• Cloud
• EC2
• Git
• Support
• Machine Learning
• PyTorch
• Python
• TensorFlow

More:

We are LexisNexis Legal & Professional, part of RELX, and we serve customers in more than 150 countries with a global team of 11,800 employees. We are a long-established leader in applying AI and advanced technologies to the legal market, delivering ethical and powerful generative AI solutions through a flexible, multi-model approach. Our team includes more than 2,000 technologists, data scientists, and experts, and we work in line with RELX Responsible AI Principles. This role is on-site/hybrid in Raleigh, NC. We support work-life balance with wellbeing initiatives, shared parental leave, study assistance, sabbaticals, and flexible working hours. The position offers a U.S. base pay range of $104,900 to $174,700, may include geographic differentials depending on location, and is eligible for an annual incentive bonus.

last updated 36 week of 2026