> Markdown version of [/jobs/ext/4604249-solutions-architect](https://www.wearedevelopers.com/jobs/ext/4604249-solutions-architect). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Solutions Architect - **Company:** SPI Global US Inc. - **Location:** United States - **Experience:** Experienced - **Contract:** Permanent contract - **Skills:** LangGraph Framework, Application Programming Interfaces (APIs), Artificial Intelligence, Data Analysis, Audit Trail, Microsoft Azure, C Sharp (Programming Language), Cloud Engineering, Computer Programming, Continuous Integration, Data Infrastructure, Information Leak Prevention, DevOps, Github, Python (Programming Language), Microsoft Data Access Components, SQL Azure, Network Virtualization, Performance Tuning, OpenAI, Azure Active Directory, Microsoft Copilot, Search Technologies, TypeScript, Enterprise Search, Microsoft Agent Framework, Office365, Retrieval-Augmented Generation, Large Language Models, Multi-Agent Systems, Prompt Engineering, IT Architecture, Hallucination Detection, Model Validation, Generative AI, Agentic-AI, Microsoft Fabric, Microsoft Copilot Studio, Information Technology, Bicep, AutoGen, Cosmos DB, Data Management, Machine Learning Operations, Prompt Injection, Azure Service Fabric, Azure AI, Model Context Protocol, Terraform, Semantic Kernel, Serverless Computing, Container Apps, Key Vault, Databricks - **Published:** November 6, 2026 - **Apply:** https://www.juju.com/job/28_25303_6a2bc77c0169d4ed2e17d7e45a23feb6 ## About the Role * Professional Experience: 8 to 12 years in software, data, or cloud architecture, including at least 2 years designing and delivering generative AI solutions, with one or more taken to production. * Azure AI Platform: Deep, hands-on expertise with Azure OpenAI and Microsoft Foundry (formerly Azure AI Foundry), Azure AI Search, Azure AI Document and Azure AI Content Safety. * Agentic AI: Practical experience building agents with frameworks such as Microsoft Agent Framework, Semantic Kernel, AutoGen, Foundry Agent Service, or LangGraph, including tool calling, multi-agent orchestration, and integration standards such as the Model Context Protocol (MCP). * Generative AI Engineering: Strong command of RAG design, embeddings and vector search, prompt engineering, context management, and model selection across commercial and open-weight LLMs. * Evaluation & Observability: Experience measuring LLM output quality and safety, and tracing and monitoring AI applications in production. * Azure Foundations: Solid knowledge of Azure PaaS, serverless and container services (Functions, App Service, AKS, Container Apps), virtual networking and private endpoints, Microsoft Entra ID, and Key Vault. * Programming & Automation: Proficiency in Python (C# or TypeScript a plus), plus Infrastructure as Code with Terraform or Bicep and CI/CD with Azure DevOps or GitHub Actions. * Security & Responsible AI: Working knowledge of AI-specific risks (prompt injection, data leakage, hallucination) and the controls that mitigate them. Preferred Skills * Experience with the Microsoft data and analytics stack (Microsoft Fabric, Azure Databricks, Cosmos DB, Azure SQL) as the data foundation for AI solutions. * Familiarity with Microsoft 365 Copilot extensibility and Copilot Studio. * Experience fine-tuning or adapting models, or deploying open-weight models on Azure. * Exposure to AI regulation and frameworks such as the EU AI Act and the NIST AI Risk Management Framework. * Consulting or client-facing delivery experience in regulated industries (financial services, healthcare, life sciences, publishing)., * Education: Bachelor's or Master's degree in Computer Science, IT, Data Science, or a related field. * Certification: Microsoft Certified: Azure Solutions Architect Expert (AZ-305) and Azure AI Engineer Associate (or its current equivalent) are highly preferred. * Leadership: Demonstrated ability to lead technical teams, mentor engineers, and explain AI architectures, risks, and trade-offs to non-technical stakeholders ## Description As an Azure AI Solution Architect at Straive, you will design and deliver the generative and agentic AI solutions that move our clients from pilots to production. With 8 to 12 years of experience, including hands-on work building LLM-powered systems, you know how to make AI solutions secure, scalable, cost-efficient, and trustworthy on Azure. You will turn complex business problems into practical AI architectures: retrieval-augmented generation (RAG) applications, copilots, and multi-agent systems that reason, use tools, and act across enterprise workflows. You will work closely with client stakeholders, data scientists, and engineering teams, and you will own the technical vision from use-case discovery through production rollout., * AI Architecture Design: Create high-level and low-level architectures for generative and agentic AI solutions on Azure, aligned with the Azure Well-Architected Framework and Microsoft's AI reference architectures. * Agentic AI Systems: Design single- and multi-agent systems that plan, call tools and APIs, and complete multi-step business workflows, including orchestration patterns, memory, human-in-the-loop checkpoints, and failure handling. * Generative AI Solutions: Architect RAG pipelines, enterprise copilots, and document intelligence solutions, covering chunking and indexing strategy, vector search, prompt design, and model selection. * Use-Case Discovery & Prioritization: Work with business stakeholders to identify high-value AI use cases, assess feasibility and data readiness, and shape them into delivery roadmaps with clear success measures. * Responsible AI, Security & Governance: Build in content safety, prompt-injection defenses, data privacy, access control, and auditability. Implement Azure Policy and governance controls so AI solutions meet enterprise and regulatory requirements. * Evaluation & LLMOps: Define evaluation frameworks for quality, groundedness, accuracy, latency, and cost. Set up monitoring, tracing, and continuous improvement for AI applications in production. * Pilot to Production: Lead solutions from proof of concept to scaled production, including integration with enterprise systems, data platforms, and existing applications. * Cost & Performance Optimization: Manage token usage, model routing, caching, and capacity planning (PTU vs. pay-as-you-go) to keep AI workloads efficient at scale. * Strategy & Consulting: Act as a trusted advisor on AI adoption, explaining trade-offs and risks to executive and non-technical audiences, and support pre-sales with solution designs and estimates. * Collaboration & Delivery: Partner with data scientists, ML engineers, developers, and DevOps teams to build automated CI/CD pipelines for AI applications and keep implementation aligned with the architecture.