AI Infrastructure Analyst

This is an office based position in Louisville, KY. What The Role Is We are seeking an AI Infrastructure Analyst, a highly capable individual contributor who designs, builds, and matures our AI platform operations while supporting the underlying Azure administration, monitoring, secure access, deployment, and service reliability. You will work independently, serve as a key technical resource for the AI platform, and strengthen our operational practices. You will design, build, and mature our AI platform harness (an MLOps / LLMOps / AgentOps / FinOps platform), own complex agent lifecycle operations, and mature our agent performance monitoring and agent and model evaluation practices. You will partner closely with IT teams and business partners, including Infrastructure Engineering, Cybersecurity, AI Solution Engineers, and Data Engineering. How You Will Spend Your Time? Position Responsibilities Include, But Not Limited To Design, build, and mature the AI platform harness by developing and enhancing the core capabilities used to run AI solutions, including monitoring, observability, model selection (AI gateway / model routing), and the catalog (model/agent registry) of available agents and models.Own complex agent lifecycle operations, managing agents through onboarding, deployment, configuration, versioning, maintenance, and retirement, and resolving non-routine lifecycle issues.Design and build agent performance and health monitoring, including dashboards, alerts, and reporting (AI observability) for agent reliability, performance, usage, latency, cost, and operational health.Establish cost visibility and optimization for AI workloads (FinOps) by building cost tracking, allocation, and reporting for models, agents, and platform services, and recommending optimizations that balance performance and spending.Mature agent and model evaluation practices by creating a repeatable approach for evaluating agents and selecting the best model and deployment option for a use case across LLMs, SLMs, open-weight models, and cloud, edge, or on-premises environments.Independently administer and support AI platform services and supporting Azure resources across production and non-production environments.Investigate and resolve complex incidents involving platform configuration, access, deployments, service dependencies, and Azure resources.Coordinate assigned platform-level changes, deployment validation, rollback planning, maintenance activities, and post-change verification.Strengthen access, identity, secrets, certificate, and governance practices in partnership with Cybersecurity and Infrastructure Engineering.Develop automation, scripting, queries, and workflow improvements that reduce manual effort and improve reliability and consistency.Evaluate operational readiness for new AI services and recommend monitoring, documentation, access, support, and recovery requirements before production use.Serve as an escalation resource for non-routine platform issues and recommend corrective actions for recurring problems.Create and maintain runbooks, operating checklists, knowledge articles, and change records that support consistent AI platform operations.Provide mentoring, knowledge sharing, and cross-training to teammates and partner teams.Participate in scheduled maintenance, after-hours support, and incident response as assigned. Who You Are… Required Skills and Experience Bachelor's degree in Information Technology, Computer Science, Information Systems, Engineering, Cloud Computing, or a related technical field.Typically 3–5 years of relevant experience in infrastructure, cloud, application, platform, monitoring, or service operations within production environments.Recent hands-on experience in areas such as Azure administration, monitoring and observability, automation, identity and access management, containers, or platform operations. Full experience specifically with Azure or AI platforms is not required.Demonstrated ability to independently resolve complex operational issues spanning multiple technical components and partner teams.Experience improving monitoring, documentation, automation, change practices, or support processes with measurable operational value.Strong judgment, problem-solving, written communication, and cross-functional collaboration skills. Preferred Qualifications And Certifications Microsoft Certified: Azure Administrator Associate or comparable demonstrated Azure administration expertise.Certified Kubernetes Administrator or comparable hands-on Kubernetes administration experience.Microsoft Certified: Azure AI Fundamentals or comparable working knowledge of AI services in Azure.Strong experience with Azure Monitor, Log Analytics, KQL, dashboards, tracing, alert tuning, and operational reporting.Experience with Entra ID, Key Vault, service principals, app registrations, secrets management, secure service exposure, or Azure governance.Automation experience using PowerShell, Python, Bash, Git-based workflows, infrastructure-as-code, or related platform tooling.Experience with AI agents, agent lifecycle management, model selection, and agent or model evaluation practices.Familiarity with LLMs, SLMs, open-weight models, and cloud, edge, or on-premises AI deployment patterns.Exposure to MLOps, LLMOps, AgentOps, or FinOps practices and tooling (referred to internally as the AI platform harness), including AI observability, AI cost management, AI gateways / model routing, or model/agent registries. Physical Requirements While performing duties of job, employee is occasionally required to: Stand; walk; use hands and fingers to handle, or feel objects, and use of computer; reach with hands and arms. Lift and/or move up to 25 pounds. Benefits Paid Vacation11 Paid HolidaysHealth, Dental & Vision eligibility from day oneFSA/HSA401K matchEAPMaternity/Paternity Leave Heaven Hill and its affiliates are committed to fostering a diverse workforce as an Equal Employment Opportunity company. We invite applications from candidates of all backgrounds, without regard to race, religion, color, sex, sexual orientation, natural origin, gender identity or expression, age, disability, veteran status, or any other legally protected characteristic.