AI Engineer II - Onsite, Springfield, MO

POSITION SUMMARY:

We are seeking an AI Engineer II to join our Information Technology team at our corporate office in Springfield, MO.
 

The AI Engineer II focuses on building and operationalizing AI solutions that align with the enterprise AI roadmap, enabling real-world applications of data intelligence and generative AI technologies.

This position bridges business needs, data infrastructure, and applied AI development to deliver scalable, secure, and production-ready systems that integrate seamlessly with enterprise platforms and data ecosystems.

This position requires working onsite in our Springfield, MO headquarters.

ESSENTIAL FUNCTIONS:  

• Collaborate with stakeholders to identify AI-driven automation and insight opportunities and define success metrics/acceptance criteria.
• Translate business needs into technical requirements and design end-to-end AI workflows, including data sourcing, orchestration, and integration points.
• Ensure data readiness by assessing availability and quality across enterprise and third-party sources; partner with Data Engineering to design and validate pipelines that produce high-quality, AI-ready datasets with data contracts, lineage, and schema-drift detection.
• Perform data preparation and transformation in SQL or Python when needed for AI workflows.
• Conduct data quality assessments, establish validation rules, maintain data lineage and data contracts, and implement schema-drift detection with automated gates; coordinate with Data Engineers to resolve integrity or availability issues.
• Design, develop, and deploy LLM-based, RAG, and generative AI solutions using modern ML/LLM frameworks and cloud AI services.
• Contribute to and implement PromptOps: maintain a versioned library of prompt/assistant patterns (system, few-shot, tool use); help teams build and optimize assistants; ensure domain alignment, structured outputs, guardrails, and prompt-injection resilience; define change control and rollback; run A/B evaluations for groundedness, accuracy, and safety with release gates; optimize for cost and latency.
• Build and operate agents and semi-autonomous workflows using established orchestration patterns, with auditable actions, step limits, feature flags/kill switches, and human-in-the-loop approvals for high-impact actions.
• Implement model lifecycle management with experiment tracking, model registry, retraining, dataset/feature and embedding/vector-index versioning, and rollback; continuously monitor performance/reliability.
• Integrate AI solutions via APIs and event-driven architectures using versioned, backward-compatible contracts with semantic versioning and a clear deprecation policy; include capacity planning and autoscaling for inference; conduct load and cost tests ahead of peak retail seasons.
• Apply MLOps and LLMOps best practices for scalable, observable, and secure deployments (containerization, orchestration, CI/CD, and model lifecycle management).
• Implement automated testing (unit, integration, contract) for AI pipelines and services.
• Partner with Data Scientists to evaluate, integrate, and productionize models, transitioning prototypes into scalable, production-ready systems.
• Ensure responsible AI governance: RBAC/IAM, secrets management, PII minimization/redaction, applicable payment-card and consumer-privacy regulations, data residency/retention, audit logging, bias detection, explainability, and compliance with governance and privacy standards.
• Research and evaluate emerging AI technologies such as agentic AI, multimodal models, and vector databases to enhance enterprise capabilities.
• Contribute to AI standards, documentation, and best practices to ensure long-term scalability and maintainability.
• Implement observability (tracing, runtime telemetry, token/cost monitoring, alerting, dashboards), define and meet SLOs/SLAs and cost budgets, enable safe rollback with runbooks; participate in an on-call rotation as needed.
• ALL OTHER DUTIES AS ASSIGNED

EXPERIENCE/QUALIFICATIONS:

• Minimum Degree Required:    Bachelor's Degree in Computer Science, Artificial Intelligence, Data Science, or related field (or equivalent experience).
• 3–5 years of hands-on experience in AI engineering, ML application development, or applied data engineering for AI workflows.
• Proficiency in Python and relevant AI/ML frameworks.
• Experience deploying LLM/RAG systems with enterprise data, including offline/online evaluation and guardrail/structured-output validation.
• Familiarity with vector databases and semantic retrieval systems.
• Solid understanding of SQL, data modeling, and data preparation for A