Senior Software Engineer - Applied AI

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.

Health insurance is one of the most confusing, high‑stakes experiences people navigate. Members don’t understand their coverage, can’t predict costs, and struggle to get answers when it matters most. We’re building the AI platform that changes that—a member experience that feels like having an expert in your corner. It’s already live. It’s already helping people. And it’s just getting started.

The next chapter is multi‑agent: specialized AI agents collaborating to answer clinical questions, navigate prior authorizations, close care gaps, and guide members through their benefits. The orchestration architecture, the agent integration patterns, and the evaluation systems that keep it all trustworthy at scale—that’s what we’re building together. You’ll shape how it’s designed and set the standard for how it grows.

• Design and build the Lang Graph‑based system that classifies member intent and routes to the right agent, ensuring stateful, context‑preserving, failure‑tolerant handling across commercial agents and internal capabilities.
• Define the agent‑integration contract: input output schemas, confidence signalling, latency SLAs, fallback behavior; the standardized pattern any new agent follows.
• Manage context across turns: maintain full member context across agent handoffs, so the platform knows prior content even after multiple turns.
• Implement guardrail and safety layer: clinical safety boundaries, PHI handling at the LLM layer, response normalization for consistent tone and compliance constraints.
• Design and operate the RAG pipeline architecture, ingesting benefits documents, formularies, and policy content via Azure AI Search; define ingestion strategy, chunking, hybrid search, and retrieval quality standards.
• Create prompt architecture: versioned prompt registry, structured output contracts, few‑shot pattern designs; testable, rollback‑able, and understandable to the team.

• Bachelor’s degree and 4–7 years of experience in software engineering.
• Experience with agentic AI in production, not just wrappers or demos; systems with multiple agents, explicit state management, and real users.
• 2–3 years building and operating production LLM or agentic AI systems.
• Can describe specific decisions in a multi‑agent system: state management, handling agent failures mid‑conversation, governance as agents are added.
• Experience with Lang Graph, Auto Gen, or a custom graph‑based orchestration in production, understanding its limits and workarounds.
• Debugged retrieval quality problems, iterated on chunking strategies, or dealt with stale knowledge bases in a live system.
• Built evaluation systems from scratch: golden datasets, automated regression, domain‑appropriate accuracy metrics, catching regressions before users.
• Experience in healthcare, insurance, fintech, or legal domains where wrong answers have consequences; designed safeguards ensuring accuracy is non‑negotiable.
• Strong Python skills, working in existing codebase, extending with AI layer.
• Target stack:
  Azure OpenAI, Azure AI Search, Azure Container Apps, Python, FastAPI, Lang Graph, Azure OpenAI / Claude via Azure, Llama Index, Lang Smith, Azure App Insights, Postgre
  
  SQL, Redis.

• Experience working in an Agile/Scrum environment.
• Creative, lateral thinker both conceptually and practically.
• Obsessed with addressing customer needs.
• Strong communication and interpersonal skills.
• Emotional intelligence.