Lead GenAI Engineer (LLM)

State Farm•Dunwoody, GA

1d•Hybrid

About The Position

State Farm’s contact centers serve as the main connection to customers, agents, and associates, handling 10’s of millions of contacts annually. Our team is building the next generation of AI and GenAI systems that put insights, intelligent applications, and automated workflows into the hands of enterprise leaders. We work at the frontier of large language models, agentic architectures, and cloud-native AI — delivering solutions that are reliable, explainable, and that enhance human decision making. Join us if you want to see your code drive decisions at scale and help customers in their time of greatest need.

Requirements

Hands-on experience building LLM-powered applications, RAG pipelines, or agentic systems
Strong foundation in software engineering: design, development, testing, and deployment of enterprise-grade applications
Experience with cloud architecture (AWS preferred), Git version control, and performance optimization
Experience with multi-agent orchestration patterns and tool-use frameworks (function calling, MCP)
Proficiency in Python and/or TypeScript for API and AI integration development
Familiarity with prompt engineering, model evaluation, and AI safety/guardrails
Experience writing clear technical documentation, test cases, and evaluation frameworks
Proficiency with AI-assisted development tools (GitHub Copilot) to accelerate delivery
Strong communication skills with the ability to explain AI concepts to non-technical stakeholders
Demonstrate initiative in learning emerging AI technologies and contributing to team knowledge

Nice To Haves

Background in insurance, financial services, or regulated industries
Familiarity with cloud Contact Center applications
Experience productionizing LLMs or GenAI features in regulated industries (insurance, financial services, healthcare)
Familiarity with AI governance, responsible AI frameworks, and enterprise

Responsibilities

Architect and implement LLM-powered applications, agentic workflows, & RAG pipelines using AWS Bedrock and AgentCore
Develop and maintain robust APIs (REST, FastAPI, etc.) serving as the backbone for AI applications, orchestration, and downstream consumers
Build pipelines that feed AI/ML systems with clean, governed, and well-structured data from enterprise sources
Build on Amazon Bedrock AgentCore primitives — Runtime, Gateway (MCP), Memory, and Code Interpreter — to deliver streaming, stateful, tool-using agents in production.
Apply prompt engineering best practices, implement guardrails, evaluate model outputs (Promptfoo, RAGAS), and ensure compliance with enterprise AI governance standards
Build and maintain cloud-native web applications that surface AI capabilities to end users, including chat interfaces, dashboards, and automation tools
Integrate AI workloads into CI/CD pipelines, apply secure coding standards, and implement observability for model behavior and inference performance
Design intuitive AI-powered interfaces that are accessible, explainable, and trusted by end users
Author technical documentation, evaluation frameworks, and contribute to internal AI communities of practice
Provide technical guidance, code reviews, and foster a culture of responsible AI innovation