AI Solution Engineer

Job Title: AI Solution Engineer
HYBRID in Washington, DC (Mandatory, no 100% remote permitted)

Job Summary: Translate how economists work into a practical solution design and ensure the Cognitive Digital Twin produces results that are transparent, traceable, and defensible.

Key Responsibilities

• Work directly with 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.

Required Experience

• 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 client-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.