AI Platform Engineer

AI Platform Engineer page is loaded## AI Platform Engineer remote type:
Hybrid locations:
Cincinnati, OH (USA) time type:
Full time posted on:
Posted Todayjob requisition :
R8913
** Be Here. Be Great.
** Working for a leader in the insurance industry means opportunity for you. Great American Insurance Group's member companies are subsidiaries of American Financial Group. We combine a "small company" culture where your ideas will be heard with "big company" expertise to help you succeed. With over 30 specialty and property and casualty operations, there are always opportunities here to learn and grow.

At Great American, we value and recognize the benefits derived when people with different backgrounds and experiences work together to achieve business results. Our goal is to create a workplace where all employees feel included, empowered, and enabled to perform at their best.

P&C IT Services provides professional services to help our business units and corporate functions use technology to create, manage, and optimize information and business processes.  IT Services can include a wide range of activities such as: software development, data management, Cloud services, IT security, network security, technical support, establishing and overseeing access rights, procuring and maintaining equipment or software, managing the infrastructure, and defining security procedures,  The overall goal of IT Services is to provide technology solutions that increase efficiency, reduce costs, and give our company a competitive advantage over our competitors.

Great American’s culture is built on connection, shared learning, and strong relationships. To support this, employees in this role are expected to be on-site a minimum of two days a week if local to Cincinnati, with the potential to work three days remotely. Core in‐office days are Tuesday and Thursday but will be determined by business needs.

The AI Platform Engineer is a hands-on engineering role building and operating the enterprise AI platform that powers our Software Developer, Data Scientist, and Knowledge Worker communities. You will design, implement, and run the platform services that make LLMs, RAG systems, and MCP servers safely consumable across the enterprise.

You will work inside a small, high-leverage platform team where code quality, automation, and operational excellence are the expectation, not the goal. You will report to the AI Platform Delivery Leader.
** What You'll Own
**** Platform Engineering
*** Build and maintain core platform services including the LLM gateway, model registry, RAG pipelines, vectorization services, and MCP server infrastructure.
* Implement AI Foundry-based capabilities and integrate them with existing enterprise platforms (API gateway, IAM, observability, ECM).
* Develop reusable Python and/or Java libraries, SDKs, and golden-path templates that let consumers onboard in under an hour.
* Own the automation that provisions access, onboards models, runs compliance checks, and emits telemetry, so platform scale is never gated by team size.
** RAG and Vectorization
*** Design and operate retrieval pipelines including chunking, embedding, vector store management, re-ranking, and evaluation.
* Tune retrieval quality against real consumer workloads and publish evaluation harnesses that let consumers measure their own RAG implementations.
* Integrate vectorization services with the ECM system and other enterprise data sources under the governance controls defined by the platform.
** MCP and Agent Infrastructure
*** Build, host, and operate MCP servers that expose enterprise capabilities safely to LLM consumers.
* Implement the authentication, authorization, rate limiting, and audit patterns that make MCP usage enterprise-ready.
* Partner with consuming teams to define and publish the MCP contracts the platform supports.
** Dev Ops and Operations
*** Treat the platform as a product: CI/CD pipelines, IaC, automated testing, progressive delivery, and full observability are table stakes.
* Own the on-call rotation for the services you build. Write the runbooks, automate the toil, and drive incident postmortems to real fixes.
* Build safety, governance,…