> Markdown version of [/jobs/ext/3056605-ai-solution-engineer](https://www.wearedevelopers.com/jobs/ext/3056605-ai-solution-engineer). 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). --- # AI Solution Engineer - **Company:** Spectraforce - **Location:** Washington, DC, United States (Remote available) - **Experience:** Experienced - **Contract:** Temporary contract - **Skills:** Artificial Intelligence, Application Integration Architecture, Application Performance Management, Microsoft Azure, BigQuery, Graph Database, Python (Programming Language), Link Analysis, Meta-Data Management, Role-Based Access Control, Power BI, Azure Active Directory, Enterprise Data Management, Digital Twin, Data Processing, Google Cloud, GitHub Copilot, Large Language Models, Data Layers, Microsoft Fabric, AI Platforms, Api Management - **Published:** September 24, 2026 - **Apply:** http://leoforce.us/Careers/Spectraforce/JobDetails.html?jobid=a437069c-b252-4d4d-b018-feeecb60270a&OrgId=1&UserId=4181 ## About the Role * 3+ years delivering data, analytics, or AI solutions. * 2+ years working with large language models, AI assistants, or agent-based systems. * Experience translating business processes into functional and technical specifications. * Demonstrated ability to work with researchers, economists, analysts, or other subject matter experts. * Strong facilitation and stakeholder engagement skills. * Ability to work onsite in Washington, DC using IMF-managed technology and development environments. Required Technologies * Python, with the ability to review and validate data-processing and AI-integration code. * Azure OpenAI and Retrieval-Augmented Generation (RAG) architectures, including grounding, retrieval strategies, and Model Context Protocol (MCP). * Azure AI Foundry evaluation capabilities and model assessment practices. * GitHub Copilot, agent specifications, instruction libraries, and AI-assisted development practices. * Claude Code and Claude Skills, including authoring and governance of instructions, skills, and behavioral guardrails. * Microsoft Fabric, OneLake, and Power BI, including architectural decision-making for enterprise data platforms. * Knowledge graph technologies, semantic modeling, ontology design, metadata management, and graph-based retrieval patterns. * Microsoft Entra ID and role-based access control. * Microsoft Purview or equivalent solutions for cataloging, lineage, governance, and auditability. Preferred * Azure API Management and Azure Monitor/Application Insights. * Responsible AI frameworks, content safety controls, and red-team testing practices. * Experience designing enterprise knowledge graphs and semantic layers for search, discovery, recommendation, and AI grounding. * Experience with Google Cloud AI services, including Vertex AI, Gemini, Agent Development Kit (ADK), and BigQuery, demonstrating cross-platform understanding of enterprise AI architectures. ## Description Job Summary: Translate how IMF economists work into a practical solution design and ensure the Cognitive Digital Twin produces results that are transparent, traceable, and defensible., * Work directly with SPR economists to understand how survey analysis is performed today and identify which activities can be automated, which require analyst review, and where AI can assist decision-making. * Document business requirements, user journeys, and solution specifications that guide engineering and AI development teams. * Define and maintain role-based prompts, agent instructions, and approved interaction patterns. * Establish and enforce evidence standards so every output can be traced back to its source survey, reporting period, methodology, and underlying calculations. * Lead the design of the project's knowledge graph and semantic model, ensuring relationships between surveys, indicators, countries, methodologies, institutions, and analytical concepts are consistently represented and reusable across agents. * Define business use cases for graph-based reasoning, including cross-country comparisons, indicator lineage, concept discovery, policy-link analysis, and expert knowledge retrieval. * Own business validation criteria, benchmark scenarios, and "golden questions" used to determine whether the solution is ready to progress beyond prototyping. * Govern the lifecycle of agent assets, including instructions, skills, knowledge sources, evaluation criteria, and governance controls. * Review AI-generated code, configurations, and solution artifacts as the accountable business and architecture reviewer. * Prepare architecture, security, governance, and review materials for EARB and other approval bodies. * Partner with data architects and engineers to ensure the knowledge graph, retrieval mechanisms, and analytical models align with business expectations and governance requirements. ## Related Videos - [Beyond Dashboards: Fixing Text-to-SQL with Semantic RAG](https://www.wearedevelopers.com/videos/2036-beyond-dashboards-fixing-text-to-sql-with-semantic-rag) - [Agentic AI - From Theory to Practice: Developing Multi-Agent AI Systems on Azure](https://www.wearedevelopers.com/videos/1532-agentic-ai-from-theory-to-practice-developing-multi-agent-ai-systems-on-azure) - [Why Your AI Agent Keeps Hallucinating Your Data: Building Deterministic Context Layers](https://www.wearedevelopers.com/videos/2055-why-your-ai-agent-keeps-hallucinating-your-data-building-deterministic-context-layers) - [Data Science in Retail](https://www.wearedevelopers.com/videos/586-data-science-in-retail) - [Data Analytics with Microsoft Fabric: End-to-End Use Case with Data Agents](https://www.wearedevelopers.com/videos/1547-data-analytics-with-microsoft-fabric-end-to-end-use-case-with-data-agents) - [Inside the AI Revolution: How Microsoft is Empowering the World to Achieve More](https://www.wearedevelopers.com/videos/869-inside-the-ai-revolution-how-microsoft-is-empowering-the-world-to-achieve-more) ## Related Articles - [How to Become an AI Engineer](https://www.wearedevelopers.com/magazine/331-how-to-become-an-ai-engineer) - [Graph and AI Trends 2026: Why Is AI Running but Not Yet Delivering?](https://www.wearedevelopers.com/magazine/680-graph-and-ai-trends-2026-why-is-ai-running-but-not-yet-delivering) - [Coffee with Developers - Maria Apazoglou - Making AI understandable for all in production](https://www.wearedevelopers.com/magazine/475-coffee-with-developers-maria-apazoglou-making-ai-understandable-for-all-in-production) - [Stephan Gillich - Bringing AI Everywhere](https://www.wearedevelopers.com/magazine/489-stephan-gillich-bringing-ai-everywhere) - [Got AI ideas but no money? Here are 10 free ways to level up your AI skills with Google Cloud](https://www.wearedevelopers.com/magazine/600-got-ai-ideas-but-no-money-here-are-10-free-ways-to-level-up-your-ai-skills-with-google-cloud) - [Navigating the AI Shift](https://www.wearedevelopers.com/magazine/629-navigating-the-ai-shift)