Senior Software Engineer - AI Operations Team; Lead Software Engineer Level

Senior Software Engineer - AI Operations Team (Open to hiring at the Lead Software Engineer Level)

• Full-time
• Department:
  Technology
• Pay Grade: 23

Why Wellmark
:
We are a mutual insurance company owned by our policy holders across Iowa and South Dakota, and we’ve built our reputation on over 80 years’ worth of trust. We are not motivated by profits. We are motivated by the well-being of our friends, family, and neighbors–our members. If you’re passionate about joining an organization working hard to put its members first, to provide best-in-class service, and one that is committed to sustainability and innovation, consider applying today!

Why Wellmark Technology?Wellmark is building innovative, modern solutions using cutting edge technology. We are driving organizational transformation and business strategy by empowering our technology team to innovate new and elegant solutions to enhance the customer experience. Together, we are leaning into the future, owning the outcome, and driving organizational change to transform how we work.

As a senior technical contributoronthe AI Platform and Operations team, you will help build and operate

Apollo, Wellmark's governed, composable foundation for safe,secureand scalableenterprise AI adoption.

You will design, build, andoperatecore AI platform capabilities including governed AI access, model routing, prompt management, agent orchestration and runtime services, tool execution, knowledge retrieval, evaluation, observability, enterprise guardrails, and cost management. You will guide engineers through complex technical challenges and driveadoptionof architecture standards, automated testing, CI/CD practices, reusable SDKs, infrastructure-as-code, templates, and reference implementations.

In partnership with product, architecture, security, compliance, legal, data governance, cloud, and engineering teams, you will strengthen platform reliability, security, auditability, and operational excellence while enabling teams across Wellmark to responsibly adopt and scale AI solutions.

Preferred:

• Experience developing cloud-native applications and platform services using Type Script, Node.js, Python, or similar technologies.
• Experience with AWS cloud services and familiarity with AI/ML capabilities such as Amazon Bedrock, Bedrock Agent Core , Sage Maker, Open Search, Lambda, API Gateway, DynamoDB,Event Bridge, Step Functions, or related services.
• Familiarity with Microsoft Azure AI services, Azure OpenAI, Azure AI Foundry, Azure AI Search, or other Azure-native AI capabilities.
• Experience designing, building, or operating AI platform capabilities such as model routing, prompt management, agent orchestration, agent runtimes, tool integration, or AI governance controls.
• Experience implementing knowledge retrieval solutions including embeddings, vector indexing, citation frameworks, semantic search, or retrieval-augmented generation (RAG) patterns.
• Experience creating reusable SDKs, APIs, templates, reference implementations, platform services, or developer self-service capabilities.
• Knowledge of identity, authentication, authorization, policy enforcement, privacy, security controls, and enterprise guardrails for AI-enabled solutions.
• Experience designing solutions for regulated environments with requirements for compliance, auditability, lineage, traceability, evidence capture, and operational governance.
• Experience implementing observability practices including tracing, metrics, logging, dashboards, alerting, incident response, platform monitoring, and operational readiness.
• Experience with AI observability and evaluation practices, including monitoring AI application quality, retrieval effectiveness, agent performance, model behavior, safety controls, and operational health.
• Experience defining, implementing, or analyzing quantitative and qualitative AI performance metrics, including accuracy, latency, cost,groundedness, hallucination detection, user feedback signals, and LLM-as-a-judge evaluation methodologies.
• Experience developing automated evaluation or quality measurement frameworks for AI applications, including models, prompts, retrieval systems, agents, safety controls, and…