Azure AI Engineer

Company Description

MomentText is a team of visionary engineers and designers committed to producing smart and ingenious solutions that defy conventional norms. By continually experimenting with novel technologies and techniques, we ensure that we remain at the forefront of our field. We prioritize critical thinking and foster an environment where our team members challenge assumptions and innovate beyond established boundaries. Our ultimate goal is to find innovative ways to enhance and revolutionize traditional industries.

Position Summary

The Principal Azure Agentic AI Engineer is responsible for architecting and deploying agentic AI solutions using Microsoft’s Azure ecosystem, including Azure AI Foundry, Semantic Kernel, and the Azure OpenAI Service. This role builds intelligent, context-aware agents that integrate across enterprise systems, enabling reasoning, orchestration, and automation at scale. The ideal candidate combines deep technical expertise in Azure AI infrastructure with a strong understanding of multi-agent orchestration, contextual retrieval, and Copilot-style integrations for enterprise productivity and decision support.

Key Responsibilities

▪ Architect multi-agent AI systems leveraging Azure OpenAI, Semantic Kernel, and vectorbased memory orchestration.

▪ Design intelligent agent frameworks capable of reasoning, planning, and tool execution across enterprise workflows.

▪Define and implement task graphs, context management strategies, and chain-ofthought persistence for agent collaboration.

▪ Configure and optimize Azure AI Foundry environments for scalable model deployment, experimentation, and governance.

▪ Integrate LLMs with Azure Cognitive Search, Data Lake, and vector retrieval layers to support context-grounded reasoning.

▪ Build connectors between agentic services and enterprise systems such as Dynamics, Power Platform, and SharePoint.

▪ Develop custom skills and functions within Semantic Kernel to extend LLM capabilities with deterministic logic and API calls.

▪ Manage orchestration pipelines for hybrid reasoning and cross-agent task routing. ▪ Implement context chaining and skill composition for reusable, modular agent behaviors.

▪ Integrate agentic systems into Microsoft 365 and enterprise workflows through Copilot extensions, Graph Connectors, and plugins.

▪ Collaborate with UX teams to design AI-assisted workflows and conversational interfaces.

▪ Ensure seamless handoff between human users and agentic systems for review, validation, and escalation. ▪ Apply Azure AI safety, compliance, and access management standards including RBAC, Managed Identity, and Conditional Access.

▪ Monitor agentic system performance, telemetry, and cost optimization across distributed deployments.

▪ Implement auditing, observability, and responsible AI guardrails aligned with enterprise governance frameworks.

Qualifications Required

▪ Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, or related technical field.

▪ Seven or more years of experience in software engineering, AI systems integration, or cloud architecture. ▪ Hands-on experience with CoPilot Studio, Azure OpenAI Service, Azure AI Foundry, and Semantic Kernel. ▪ Proven expertise in LLM orchestration, vector-based retrieval, and multi-agent design.

▪ Proficiency in Python, C#, and RESTful API development for Azure functions and microservices.

▪ Strong understanding of Azure Cognitive Search, Data Factory, and Event Grid architectures.

Preferred

▪ Experience building Copilot extensions or plugins for Microsoft 365 or Dynamics 365.

▪ Familiarity with LangChain, AutoGen, or other agentic orchestration frameworks.

▪ Knowledge of MLOps, CI/CD, and Azure DevOps pipelines for AI deployment.

▪ Background in knowledge management systems, RAG architectures, or enterprise copilots.

▪ Microsoft Certified: Azure Solutions Architect Expert or Azure AI Engineer Associate.

Core Competencies

▪ Deep expertise in Azure’s AI and agentic services ecosystem.

▪ Strong architectural and system design skills for large-scale AI deployments.

▪ Ability to bridge LLM reasoning with enterprise tools and data.

▪ Commitment to responsible AI, data governance, and secure model operations.

▪ Proven ability to translate business processes into intelligent, autonomous workflows.