Experienced AI Engineer - Generative AI/Machine Learning

rlicorp; Chicago (IL); On-site; USD 150,000 - 210,000; Full time

Job summary

RLI is seeking an experienced Principal AI Engineer to design, develop, and deliver next‑gen AI solutions across the enterprise. You will build scalable cloud-native applications, integrate AI capabilities with enterprise systems, and mentor engineers to raise quality standards.

The role emphasizes collaboration with product owners, architects, and business stakeholders to solve complex business challenges using AI, LLMs, RAG, and AI agents within secure, scalable architectures.

Qualifications

• Bachelor's degree in computer science or related field.
• 7+ years designing and supporting enterprise apps.
• Experience building cloud-native, distributed systems and RESTful APIs.
• Experience with LLMs, RAG, AI agents, and prompt engineering.
• Experience with vector databases, embeddings, semantic retrieval.
• Familiarity with AI-assisted development tools to improve delivery.
• Proficient in Agile with Git-based workflows and CI/CD.

Responsibilities

• Design, develop, test, and deploy enterprise AI apps.
• Build intelligent solutions with LLMs, RAG, AI agents, and workflows.
• Develop scalable backend services and cloud-native apps.
• Design integrations using APIs, messaging, and event-driven architectures.
• Develop document processing, OCR, and knowledge extraction solutions.
• Design vector search, semantic retrieval, and knowledge base solutions.
• Deploy, manage, and optimize apps in Kubernetes environments.
• Collaborate with partners to translate needs into AI solutions.
• Participate in architecture reviews, code reviews, Agile ceremonies.
• Contribute to CI/CD pipelines, IaC, and software quality practices.
• Mentor team members and promote high standards for software quality.

Skills

Python

Cloud architecture

LLMs

REST APIs

Distributed systems

AI agents

Prompt engineering

Git

CI/CD

Education

Bachelor's degree in CS

Tools

Kubernetes

Docker

LangGraph

LangChain

Azure AI Foundry

GitLab CI/CD

REST APIs

IaC

Job description

About Us

We're not like other insurance companies. From our specialty products to our business model, our culture to our results - we're different. Different is who we are, and how we work, interact, deliver and succeed together. Creating a different and better insurance experience doesn't just happen. It takes focus and a shared passion for going beyond the expected to forge relationships and deliver care that makes a difference. This approach rises from and is supported by our talented, ethical and smart team of employee owners united around a single purpose: to work alongside our customers and partners when they need us, in unexpected ways, with exceptional results.

RLI is a Glassdoor Best Places to Work company with a strong, successful background. For decades, our financial track record has been stellar - a testament to our culture and validation of our reputation as an excellent underwriting company.

Position Purpose

Under general management, design, develop, and deliver next-generation AI solutions that improve business processes across the enterprise. Develop intelligent applications, integrate AI capabilities with enterprise systems, and build scalable cloud-native solutions that enable automation, knowledge discovery, and operational efficiency. Collaborate with product owners, architects, business stakeholders, and development teams to design secure, scalable, and maintainable AI-enabled solutions that solve complex business challenges.

Principal Duties & Responsibilities

• Design, develop, test, and deploy enterprise AI applications using modern software engineering practices.


• Build intelligent solutions utilizing Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), AI agents, and workflow orchestration technologies.


• Develop scalable backend services, REST APIs, and cloud-native applications that integrate AI capabilities with enterprise systems.


• Design and implement integrations using APIs, messaging, and event-driven architectures.


• Develop document processing, OCR, and knowledge extraction solutions using AI technologies.


• Design and implement vector search, semantic retrieval, and enterprise knowledge base solutions.


• Deploy, manage, and optimize applications within Kubernetes-based environments.


• Collaborate with business partners to understand business needs and translate them into practical AI-enabled solutions.


• Participate in architecture reviews, code reviews, Agile ceremonies, technical planning, and solution design discussions.


• Contribute to CI/CD pipelines, infrastructure automation, and software engineering best practices.


• Mentor team members and promote high standards for software quality, testing, security, observability, and maintainability.


• Assist with special projects or perform other duties as assigned.

Education & Experience

• Typically requires a Bachelor's degree in computer science or a related field


• Minimum of 7 years of professional software engineering experience designing, developing, and supporting enterprise applications. Equivalent combination of education and experience will be considered.


• Experience designing and developing cloud-native applications, distributed systems, and RESTful APIs.


• Experience developing AI-enabled applications utilizing Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), AI agent frameworks, and prompt engineering techniques.


• Experience designing and implementing vector databases, vector search, embeddings, and semantic retrieval solutions.


• Experience using AI-assisted software development tools to improve software design, development, testing, and delivery.


• Experience working within Agile software development environments utilizing Git-based source control and CI/CD practices.

Knowledge, Skills, & Competencies

• Strong proficiency in Python and modern software engineering principles.


• Strong understanding of software architecture, object-oriented design, and design patterns.


• Ability to design and develop scalable cloud-native applications utilizing Kubernetes, Docker, REST APIs, and microservices.


• Knowledge of modern AI application architecture including Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), AI agents, LangGraph, LangChain, Azure AI Foundry, prompt engineering, and AI model evaluation.


• Ability to design and implement vector search, semantic retrieval, embeddings, and knowledge ingestion pipelines for enterprise AI solutions.


• Knowledge of intelligent document processing technologies including OCR, document processing pipelines, and structured and unstructured document extraction.


• Experience integrating enterprise systems using APIs, messaging, and event-driven architectures.


• Knowledge of DevOps tools and practices including Git, GitLab, GitLab CI/CD, Infrastructure as Code (IaC), and automated deployment pipelines.


• Ability to leverage AI-assisted development tools while maintaining high standards for software quality, security, testing, and ob