AI Application Developer

MGRM Pinnacle Inc. Location: Tempe, Arizona Work Arrangement: This is a full-time, on-site position. Remote work is not available for this role. About the Role MGRM Pinnacle Inc. is seeking an experienced AI Application Developer to design, build, and deliver complete AI-enabled applications across our healthcare, education, compliance, and citizen-facing technology platforms. This is not a role focused solely on adding AI features to existing applications. We are looking for a strong software engineer who can think across the entire application—from architecture, backend services, APIs, and data models to front-end user experience—and determine how AI should be integrated into the product from the ground up. The ideal candidate combines solid full-stack application development experience with hands-on experience building applications that use large language models (LLMs), retrieval-augmented generation (RAG), AI assistants, summarization, classification, or agentic workflows. Key Responsibilities End-to-End Application Development Design and build complete AI-enabled applications from architecture through deployment. Develop backend services, APIs, data models, and user-facing application components. Build responsive front-end experiences using modern frameworks such as React, Vue, or Angular. Integrate new applications with existing enterprise systems and shared data sources. Translate business and operational requirements into secure, scalable technical solutions. AI & LLM Development Build AI capabilities including RAG-based search, summarization, classification, copilot-style assistants, and multi-step agentic workflows. Integrate applications with locally hosted and enterprise-managed LLM environments. Design, test, version, and improve production prompt templates. Develop evaluation methods and test sets to measure AI output quality and reliability. Identify and mitigate hallucination, accuracy, latency, context-window, and other LLM-related risks. Secure & Reliable Development Develop applications in accordance with established security and data-classification requirements. Follow secure coding practices and build applications capable of passing automated security and code-quality checks. Write unit and integration tests to support reliable releases. Follow appropriate secrets-management and credential-handling practices. Maintain clear technical documentation for the applications you develop. Collaboration & Product Ownership Work with product, engineering, compliance, healthcare, education, and other stakeholders to translate business needs into working applications. Take ownership of assigned applications and features from initial design through testing and release. Participate in code reviews, technical design discussions, and Agile/Scrum development processes. Support documentation and evidence requirements for applications operating in regulated environments. Required Qualifications Approximately 5 years of professional software engineering experience, including experience building and shipping production applications. At least 2 years of hands-on experience developing AI/LLM-based applications. Experience developing across the application stack, including backend services, APIs, databases, and front-end interfaces. Strong programming experience with one or more of the following: Python (FastAPI or Django). Java. Node.js. TypeScript. Experience with a modern front-end framework such as React, Vue, or Angular. Experience designing or consuming REST and/or GraphQL APIs. Experience working with SQL databases and at least one NoSQL data store. Experience with Git-based development workflows, unit testing, and integration testing. Hands-on experience building at least one meaningful AI-based application using an LLM in production or in a substantial production-oriented prototype. AI Experience We Are Looking For Candidates should have practical experience with one or more of the following: Retrieval-Augmented Generation (RAG). Prompt engineering and prompt templating. AI-powered search. Summarization or classification applications. Copilot-style assistants. Agentic or multi-step AI workflows. LangChain, LlamaIndex, or similar orchestration frameworks. Vector databases such as pgvector, Qdrant, or Milvus. Ollama, vLLM, or similar model-serving environments. Evaluating LLM output for quality, accuracy, and hallucination risk. Please note: Using ChatGPT or an AI coding assistant to help write code is not, by itself, the type of AI development experience we are seeking. Candidates should be able to discuss an application they have built that actually calls and uses an AI model as part of the product. Additional Skills That Are Helpful Experience in any of the following areas is beneficial but not required: Docker. GitHub Actions or GitLab CI. Postman or API testing. Kubernetes fundamentals. Kong API Gateway. OWASP Top 10 and OWASP LLM Top 10. Healthcare technology or HL7/FHIR APIs. Government or e-governance applications. Regulated or sensitive-data environments. ISO/IEC 27001 or ISO/IEC 42001. CMMI-aligned software development environments. Who Will Be Successful in This Role You may be a strong fit if you: Think about the complete application rather than only the AI model or feature. Have personally built an AI-enabled application and can explain its architecture, data flow, AI components, and user experience. Enjoy solving the practical challenges of LLM applications, including hallucination, latency, evaluation, context limits, and reliability. Are comfortable owning an application from initial requirements through development, testing, and release.Approach prompt development with the same discipline as software development-testing. Can work with both technical and non-technical stakeholders to turn an idea or business requirement into a practical working application. Value secure, well-documented development practices, particularly when working with sensitive or regulated information. About MGRM Pinnacle Inc. MGRM Pinnacle Inc. is part of MGRM Group, a multi-domain organization with technology and service initiatives spanning healthcare, education, compliance, e-governance, and related digital platforms. Our technology teams develop and support platforms serving complex operational environments where security, reliability, usability, and responsible use of AI are critical. #J-18808-Ljbffr MGRM