AI Solutions Engineer (Full Stack)

The AI Solutions Engineer (Full Stack) will design, build, and deploy internal AI-powered tools and assistants that improve productivity, enhance decision-making, and support profitable growth. This role will focus on engineering and integration-developing AI assistants, Model Context Protocol (MCP) clients and servers, and robust Retrieval-Augmented Generation (RAG) solutions-rather than on custom statistical or machine-learning model development. The AI Solutions Engineer will work across the full stack (front-end, back-end, cloud, and data services) using technologies such as Python and AI Foundry to operationalize AI capabilities securely and reliably.

will partner closely with IT and business stakeholders to translate use cases into scalable, maintainable AI applications aligned with Carlisle's Vision 2030. This role will report to the Senior Director of Emerging Technology and Business Analytics. This job will be expected to perform duties Monday - Friday, 8am - 5pm. This job will require up to 15% travel for the calendar year. Duties and

: • Partner with IT and business stakeholders to identify, design, and deliver AI-powered assistants and internal tools that automate workflows, improve user experience, and support profitable revenue growth. • Design, develop, and deploy AI assistants and agents using large language models, RAG pipelines, and enterprise data sources. • Build, integrate, and maintain MCP (Model Context Protocol) clients and servers to connect AI assistants with internal systems, APIs, and tools. • Design and implement RAG architectures, including: • Document ingestion, chunking, and enrichment • Embedding generation and storage in vector databases • High-quality retrieval, grounding, and response generation • Evaluation and continuous improvement of RAG quality • Develop full stack applications and services that expose AI capabilities, including: • Front-end components (web UIs, dashboards, or plug-ins) • Back-end APIs and microservices (primarily in Python) • Integration with identity, authentication, and logging/monitoring systems • Use AI Foundry (e.g., Azure AI Foundry or similar platforms) to configure models, orchestrate prompts/flows, and manage deployment environments. • Collaborate with infrastructure, security, and data teams to ensure AI solutions meet Carlisle standards for data security, reliability, quality, and governance. • Implement best practices for code quality, observability, and operations (e.g., CI/CD, automated testing, monitoring, and alerting) for AI applications. • Develop and maintain documentation, reference implementations, and reusable components that accelerate future AI assistant development. • Stay current on emerging AI/LLM technologies, tools, and frameworks (e.g., MCP, RAG frameworks, orchestration libraries) and assess their fit for Carlisle's environment. • Provide occasional support and training to internal users and teams adopting AI assistants and tools. Required Knowledge/Skills/Abilities: • Strong software engineering and full stack development skills, with: • Proficiency in Python required • Experience with modern web frameworks and front-end technologies (e.g., JavaScript/TypeScript, React, Vue, or similar) preferred • Hands-on experience building and deploying AI- or LLM-powered applications, particularly: • AI assistants, chat interfaces, or agents • RAG-based solutions grounded in enterprise data • Experience with AI Foundry (e.g., Azure AI Foundry) or comparable enterprise AI platforms to configure models, prompts, and pipelines. • Experience with closed and open source large language models (e.g., OpenAI, Anthropic, Google) and their APIs. • Practical experience with: • Retrieval-Augmented Generation frameworks for large language models • Vector databases and search technologies (e.g., Azure AI Search, Pinecone, Weaviate, or similar) • Handling and storing unstructured data (documents, text, media) using NoSQL and vector databases • Experience building and consuming APIs and services, including: • RESTful APIs (required); GraphQL or gRPC (preferred) • MCP clients and servers or similar plugin/protocol-based integrations • Understanding of and ability to implement a full stack of software tools to deploy AI solutions, including: • Front-end applications or integrations • Cloud and container environments (e.g., Docker, Kubernetes) • Databases and message queues • CI/CD pipelines and infrastructure-as-code concepts • Familiarity with core AI/ML and LLM concepts (prompts, grounding, hallucination mitigation, evaluation), with an emphasis on application and integration rather than custom model training. • Strong focus on security, governance, and compliance when working with enterprise data and AI services. • Outstanding verbal and written communication skills, with the ability to explain technical concepts to non-technical stakeholders. • Strong analytical, debugging, and root-cause problem-solving skills. • Ability to work in an agile environment and collaborate effectively with cross-functional teams.