Software Engineer

At Blue Cross and Blue Shield of Nebraska, we are a mission-driven organization dedicated to championing the health and well-being of our members and the communities we serve.

Our team is the power behind that promise. And, as the industry rapidly evolves and we seek ways to optimize business processes and customer experiences, there’s no greater time for forward-thinking professionals like you to join us in delivering on it! As a member of Team Blue, you’ll find purpose, opportunities and the support you need to build a meaningful career and make a powerful impact in our community.

The Software Engineer position will be responsible for working with cross-functional business teams to research, design, test, and maintain various systems and applications. This role is responsible for providing engineering knowledge and experience, as needed, to deliver solutions to the business both on new builds, as well as support on modifications and maintenance for existing programs.

What you'll do:

Your primary focus is agent design and orchestration. 

• Multi-agent orchestration layer. Design and build the LangGraph-based system that classifies member intent and routes to the right agent. Stateful, context-preserving, failure-tolerant. Handles commercial agents and internally built capabilities through the same interface. 

• Agent integration contract. The standardized pattern that makes any agent pluggable: input schema, output schema, confidence signaling, latency SLA, fallback behavior. When the team integrates a new agent, they follow a pattern you designed. 

• Context management across turns. Multi-turn conversations that maintain full member context across agent handoffs. The member asks a follow-up two turns later; the platform knows what was said, which agent handled it, and what was retrieved. 

• Guardrail and safety layer. Clinical safety boundaries, PHI handling at the LLM layer, and response normalization ensuring every agent response arrives in a consistent tone and within compliance constraints regardless of which agent generated it. 

• RAG pipeline architecture. Benefits documents, formularies, and policy content retrieval via Azure AI Search. You define the ingestion strategy, chunking approach, hybrid search configuration, and retrieval quality standards. 

• Prompt architecture. Versioned prompt registry, structured output contracts, few-shot pattern design. Every prompt is testable, rollback-able, and understandable by the team. 

To be considered for this position you must have:

• Bachelor’s degree and 2-4 years of experience in software development.

Experience with agentic AI in production—not LLM wrappers, not single-agent chatbot demos, not RAG tutorials. Systems with multiple agents, explicit state management, and real users depending on the answers being correct. 

• 1-2 years building and operating production LLM or agentic AI systems 

• You can describe specific decisions you made in a multi-agent system: state management approach, how you handled agent failures mid-conversation, how you kept the system governable as agents were added 

• LangGraph, AutoGen, or custom graph-based orchestration used in production, not just evaluated. You know where it breaks down and how you worked around it 

• Debugged retrieval quality problems, iterated on chunking strategies, dealt with stale knowledge bases in a live system with real users 

• Built evaluation systems from scratch: golden datasets, automated regression, domain-appropriate accuracy metrics. Your eval suite caught a production regression before users reported it 

• Experience in healthcare, insurance, fintech, or legal domains—AI systems where a wrong answer has consequences, and you designed the safeguards that make accuracy non-negotiable 

• Strong knowledge of Python. Work in an existing codebase and extend it with the AI layer 

• Azure OpenAI, Azure AI Search, Azure Container Apps are the t