About the Role
Radian is seeking an Associate Generative AI Engineer to help design, build, and deploy enterprise-grade Generative AI solutions across a growing portfolio of business use cases. This role offers hands-on experience with production LLM applications, agentic AI systems, and AWS-based AI architectures, with a clear path to long-term growth.
This position is ideal for an engineer who has foundational experience with modern AI/ML development and wants to deepen their expertise in LLMs, Retrieval-Augmented Generation (RAG), and intelligent automation within a real-world enterprise environment.
What You'll Do
Design, develop, and deploy Generative AI solutions using leading LLMs such as GPT, Claude, and Gemini
Build and integrate AI-driven applications within the AWS ecosystem, leveraging AI/ML services for model usage, governance, and scalability
Contribute to the development of agentic AI systems that enable reasoning, planning, and automated task execution
Develop use cases including:
Document processing and summarization
Retrieval-Augmented Generation (RAG) solutions
Intelligent workflows and reasoning pipelines
Implement and support RAG frameworks and vector databases
Write clean, scalable code primarily in Python, with some development in Node.js
Optimize and fine-tune models and AI workflows for performance, cost-efficiency, and reliability
Troubleshoot AI model behaviors, integrations, and production issues
Collaborate with Program Managers, engineers, and external consulting partners on AI initiatives
Participate in Agile ceremonies and contribute to iterative solution delivery
Document AI architectures, workflows, and technical implementations
Communicate technical concepts and AI capabilities to non-technical stakeholders
Required Qualifications
2+ years of experience building or integrating Generative AI or AI/ML solutions
Hands-on experience working with Large Language Models (LLMs)
Experience developing solutions within the AWS cloud environment
Strong proficiency in Python
Working knowledge of Node.js
Experience with RAG architectures and vector databases
Understanding of AI application design, data pipelines, and model integration patterns
Ability to work in a fast-paced, collaborative Agile environment
Preferred Qualifications
Experience in financial services, insurance, or regulated industries
Exposure to large-scale system modernization or claims platform transformation initiatives
Familiarity with agentic AI or autonomous AI workflows
Experience with AI-assisted development tools (e.g., GitHub Copilot)
Experience working with external vendors or consulting partners
Work Environment
Hybrid preferred, candidates within commuting distance to Wayne, PA with occasional onsite presence
Remote candidates considered if able to work EST hours
Standard 40-hour work week, with occasional additional hours based on project needs
#REMOTE #LI-MB1