> Markdown version of [/jobs/ext/4169636-sr-software-engineer](https://www.wearedevelopers.com/jobs/ext/4169636-sr-software-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Sr Software Engineer - **Company:** Blue Cross Blue Shield - **Location:** Omaha, NE, United States - **Experience:** Expert - **Contract:** Permanent contract - **Skills:** LangGraph Framework, Artificial Intelligence, Microsoft Azure, Software Debugging, Python (Programming Language), PostgreSQL, Scrum Methodology, Redis, OpenAI, Software Engineering, Enterprise Search, Retrieval-Augmented Generation, Large Language Models, Multi-Agent Systems, Llamaindex, Agentic-AI, Fastapi, LangSmith, AutoGen, Claude, Container Apps - **Published:** October 21, 2026 - **Apply:** https://diversityjobs.com/career/18715481/Sr-Software-Engineer-Nebraska-Omaha ## About the Role * Bachelor's degree and4-7 years of experience in software engineering. 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. * 2-3 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 legaldomains-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 target stack The strongest candidates will also have: * Experience working in an Agile/Scrum environment. * Desire to think in a creative, lateral way both conceptually and in practical application. * You must be obsessed with addressing customer needs. * Strong communicationand interpersonal skills. * Possess emotional intelligence. The Stack Python /FastAPI *LangGraph * Azure OpenAI / Claude viaAzure * Azure AISearch * Azure ContainerApps *LlamaIndex *LangSmith * Azure AppInsights *PostgreSQL * Redis To perform this job successfully, an individual must be able to perform each essential duty satisfactorily. The requirements listed are representative of the knowledge, skill,and orabilityrequired. Reasonableaccommodationsmay be made to enable individuals with disabilities to perform the essential functions. Other duties may be assigned. Ready to make an impact? Join a team where your skills, attitude, and ideas are valued-and whereyou'llhelp shape the future of healthcare technology. ## Description * Multi-agent orchestration layer.Design and build theLangGraph-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 teamintegratesa new agent, they follow a pattern you designed. * Context management across turns.Multi-turn conversations thatmaintainfull member context across agent handoffs. The memberasksa follow-up two turnslater; 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, andretrievalquality standards. * Prompt architecture.Versioned prompt registry, structured output contracts,few-shot pattern design. Every prompt is testable,rollback-able, and understandable by the team.