AI Platform Engineer

AI Platform Engineer

The Aspen Group (TAG) is one of the largest and most trusted retail healthcare business support organizations in the U.S., supporting over 23,000 healthcare professionals and team members at more than 1,150 locations across 48 states. Our five supported healthcare practices operate under the brands Aspen Dental, ClearChoice, WellNow, Chapter Aesthetic Studio, and Lovet. We're committed to enabling healthcare professionals to focus on patient care while we handle the business operations that support them.

We are seeking an AI Platform Engineer.

Our Platform Engineering organization — spanning Delivery, Cloud, and SRE — is expanding to lead and maintain the company's AI platform across the business. We're hiring an AI Platform Engineer to own the foundation that lets every team use AI safely, reliably, and productively — built on Google Cloud and anchored by our two flagship enterprise AI platforms: Claude Enterprise and Google's Vertex AI (Gemini Enterprise Agent Platform).

In this hands-on role you'll:

• Operate and extend these platforms
• Manage the end-to-end onboarding of users and teams onto them
• Curate and govern the surrounding ecosystem of plugins, connectors, and marketplace extensions
• Build the agents, tooling, and paved paths that turn AI from a novelty into everyday infrastructure.

You'll do this on Google Cloud, increasingly through the Gemini Enterprise Agent Platform (formerly Vertex AI). It's a high-impact position with significant room to grow as our AI practice matures.

This is a strong fit for an engineer with a few years of Platform Engineering, DevOps, SRE, or MLOps experience who is excited about AI enablement; someone who likes owning a platform end to end, from provisioning and onboarding through operations and governance.

Responsibilities

AI Platform Operations & LLMOps (on Google Cloud)

• Deploy, scale, and operate Claude Enterprise, Gemini Enterprise, and related AI/LLM workloads in production (be it Google Cloud or Anthropic); keeping them reliable, performant, and cost-effective.
• Build and maintain CI/CD pipelines, infrastructure-as-code, and deployment automation for AI applications, agents, and models, increasingly on the Gemini Enterprise Agent Platform (formerly Vertex AI).
• Instrumentation of AI systems with monitoring, logging, and observability (tracking latency, quality, usage, and spend) and responding to issues as part of an on-call rotation.
• Manage integrations with model providers and APIs (Claude, Gemini, and code assistants), including authentication, rate limits, quotas, and failover.

Onboarding & User Lifecycle Management

• Own the end-to-end onboarding experience for Claude Enterprise and Gemini Enterprise: provisioning, license/seat assignment, SSO, and group/role configuration.
• Manage the full user lifecycle — onboarding, role changes, and deprovisioning — keeping access, entitlements, and seat assignments accurate and auditable.
• Build automation and self-service flows so new users and teams get access to approved AI tools, with the right permissions, from day one.
• Track adoption and seat utilization, and partner with IT and Security on identity, access reviews, and provisioning workflows.

Platform Extensions & Marketplace

• Manage and curate platform extensions across our AI stack — Claude Enterprise plugins, connectors, and MCP integrations, plus Gemini Enterprise / Agent Platform extensions (Agent Garden, Model Garden, connectors).
• Run the internal marketplace/catalog of approved extensions, agents, and integrations: review, vet, publish, version, and retire them.
• Define how extensions are requested, evaluated, and governed — balancing easy self-service adoption against security and data-handling requirements.
• Build and integrate custom plugins, connectors, and MCP servers that link our AI platforms to internal systems and data.

Internal AI Tooling & Paved Paths

• Build internal tools, copilots, and agents — on the Gemini Enterprise Agent Platform and Claude — that make it easy for teams to adopt AI in their workflows.
• Develop reusable templates, reference architectures, and libraries for common patterns (RAG, summarization, agents, evaluations).
• Integrate AI capabilities into existing internal systems and the developer toolchain.

Enablement & Training

• Help engineers and other teams adopt approved AI tools through clear documentation, office hours, demos, and hands-on support — tightly linked to onboarding.
• Create and maintain best-practice guides, prompt libraries, and onboarding materials.
• Gather feedback from users to prioritize platform improvements and surface new opportunities.

Governance & Best Practices

• Help define and implement standards, guardrails, and policies for safe, secure, and responsible AI use (data handling, access control, acceptable use) — including for plugins, extensions, and the marketplace.
• Build evaluation harnesses and quality checks to measure AI output quality and catch regressions.
• Partner with Security, IT, and leadership on compliance, access provisioning, and cost governance.

Requirements

• 3–5 years in platform engineering, DevOps, SRE, MLOps, backend, or a similar software/infrastructure role.
• Strong programming skills in Python, plus comfort with at least one other language (JavaScript/TypeScript, Go, or Java a plus).
• Hands-on experience with Google Cloud (GCP) as a primary cloud platform — AWS or Azure experience is welcome, but GCP is central to this role.
• Working knowledge of how LLMs and AI APIs are used in applications (prompting, RAG, embeddings, tool/function calling, agents) — or strong fundamentals and clear eagerness to learn.
• Experience with containers and orchestration (Docker, Kubernetes) and infrastructure-as-code (Terraform or similar).
• Experience building and operating AI Delivery workstreams and production services.
• Experience with identity, access, and provisioning — SSO/SAML/SCIM, role and group management, and user lifecycle (onboarding/deprovisioning).
• Solid grasp of AI monitoring/observability and operational best practices.
• Clear written and verbal communication; able to explain technical concepts to non-experts and write strong documentation — important for onboarding and enablement.
• Based in (or willing to relocate to) the Chicago area and able to work onsite/hybrid.

Nice to Have (Preferred)

• Direct experience with Claude Enterprise — deployment, administration, onboarding, plugins, connectors, or MCP.
• Experience with Gemini Enterprise and/or the Gemini Enterprise Agent Platform (formerly Vertex AI) — Agent Builder/Agent Engine, Agent Garden, Model Garden, RAG/Vector Search.
• Experience managing and creating platform extensions, a plugin ecosystem, or an internal app/agent marketplace.
• Direct experience with LLMOps/MLOps tooling — model serving, vector databases, evaluation frameworks, agent orchestration (e.g., ADK, LangChain/LlamaIndex).
• Experience deploying or integrating enterprise AI tools (e.g., Claude, Gemini, GitHub Copilot, NotebookLM) across an organization.
• Experience building internal developer platforms or developer-experience tooling.
• Familiarity with AI governance, security, or responsible-AI frameworks.
• Experience running enablement, training, or developer-advocacy programs.
• Familiarity with our stack: Google Cloud / BigQuery, Atlassian (Jira/Confluence), incident.io, Grafana/OTEL, Sentry, Microsoft 365.
• Degree in Computer Science, Engineering, or a related field — or equivalent practical experience.

About the Team

You'll join our Platform Engineering organization, which spans Delivery, Cloud, and SRE and reports to the Senior Director of Platform Engineering. We're a pragmatic team focused on giving the rest of the company reliable, well-paved infrastructure to build on — and we're now extending that mission to AI.

*This role is onsite 4 days/week in our Chicago office (Fulton Market District)

• A generous benefits package that includes paid time off, health, dental, vision, and 401(k) savings plan with match
• $111,000-135,00