AI Engineer (Full-Stack)

AI Engineer (Full Stack)NO SPONSORSHIP AVAILABLEJob SummaryWe are seeking an AI Engineer with a strong software engineering foundation and hands-on experience building production-grade AI applications. This role is ideal for a full stack engineer who has evolved into AI development and understands how to design, develop, and deploy intelligent applications powered by Large Language Models (LLMs).The ideal candidate is an experienced software developer with end-to-end application development experience, deep knowledge of modern AI architectures, and experience deploying solutions in AWS or Azure cloud environments.Key ResponsibilitiesDesign, develop, and maintain AI-powered applications from backend services through user-facing interfaces.Build and integrate conversational AI solutions using Large Language Models (LLMs) and modern AI frameworks.Design AI architectures that effectively manage conversational context, memory, and multi-turn interactions to deliver accurate and context-aware responses.Develop AI skills, plugins, and instruction-based components that enable LLMs to perform specialized business functions.Create, test, and optimize prompts, workflows, and AI orchestration logic.Integrate AI services with enterprise applications, APIs, databases, and third-party systems.Deploy and manage AI solutions within AWS or Azure cloud environments.Collaborate with cross-functional teams to translate business requirements into scalable AI solutions.Implement best practices for software architecture, testing, security, monitoring, and performance optimization.Required QualificationsStrong software engineering background with experience building full stack applications.Experience developing backend services and APIs, with the ability to contribute across the full application stack. Candidates with stronger backend expertise are encouraged to apply.Hands-on experience building production AI applications using Large Language Models (LLMs).Solid understanding of conversational AI architecture, including how conversational context is maintained and managed across multiple user interactions.Experience creating AI skills, plugins, or instruction-based components that extend LLM capabilities and orchestrate AI workflows.Ability to clearly explain AI architecture decisions and how AI components interact within an application.Experience working with cloud platforms such as AWS or Microsoft Azure.Strong knowledge of software engineering best practices, including version control, testing, API development, and CI/CD.Preferred QualificationsExperience with Semantic Kernel, AI skills, or similar plugin-based AI frameworks.Experience with Microsoft AI ecosystem, Azure AI Services, or Azure OpenAI.Experience with Retrieval-Augmented Generation (RAG), vector databases, embeddings, and AI agents.Familiarity with AI evaluation, observability, and model performance optimization.Experience deploying containerized applications using Docker and Kubernetes.What Will Make You Stand OutCandidates will stand out if they can:Demonstrate a strong understanding of conversational context management and explain how AI systems maintain context across multi-turn conversations.Walk through how they have created and implemented AI skills, plugins, or instruction files that guide LLM behavior.Discuss experience with AI orchestration frameworks, particularly Microsoft Semantic Kernel. Experience with AI skills and Semantic Kernel's plugin architecture is a significant plus.Explain the architecture behind production AI applications rather than simply consuming AI APIs.Show experience deploying scalable AI solutions in AWS or Azure cloud environments.