Microsoft Fabric / Power BI / Data Architecture

Must Have Technical/Functional Skills • 8+ years of experience in software engineering, analytics, business intelligence, or AI application development • Hands-on experience with Microsoft Fabric, including OneLake, Lakehouse or Warehouse, Power BI semantic models, and Power BI Embedded • Working knowledge of Fabric IQ concepts, including ontologies, business entities, relationships, graph-based context, and agent-ready semantic layers. • Strong experience developing modern web applications using React 18.x or 19.x, TypeScript, JavaScript, reusable UI components, and REST APIs. • Experience building AI-led reports and AI-embedded analytics, including natural-language interaction, automated narratives, anomaly or trend explanations, recommendations, and conversational analytics. • Hands-on experience with Azure OpenAI or comparable large language model services, prompt engineering, retrieval-augmented generation, semantic search, and AI evaluation. • Strong understanding of report discovery, persona and use-case analysis, KPI definition, data lineage, semantic modeling, and report rationalization. • Ability to rapidly prototype 2 to 3 high-value reports and convert discovery findings into epics, features, user stories, acceptance criteria, estimates, dependencies, and a prioritized backlog. • Experience defining reusable architecture patterns, report templates, React components, prompt libraries, semantic models, and governance controls for enterprise-scale adoption. • Strong SQL skills; proficiency in Python or C# is preferred. Experience integrating structured and unstructured enterprise data is desirable. • Excellent facilitation, stakeholder management, communication, and storytelling skills for both technical and executive audiences. Roles & Responsibilities • Lead discovery workshops with business, product, data, UX, security, and technology stakeholders to understand current reports, decisions supported, user journeys, pain points, KPIs, data sources, and regulatoryconstraints. • Assess the existing reporting landscape and classify reports for modernization, consolidation, redesign, reuse, or retirement using agreed business-value, complexity, risk, and usage criteria. • Select and develop an initial set of 2 to 3 representative AI-powered report prototypes that demonstrate measurable business value and establish reusable implementation patterns. • Design AI-led reports that proactively surface insights, drivers, trends, exceptions, contextual narratives, and recommended next actions instead of presenting static metrics alone. • Build AI-embedded report experiences in React and Power BI Embedded, including conversational interfaces, natural-language exploration, guided analysis, explainable insights, and role-aware experiences. • Develop and align Fabric IQ ontologies, Power BI semantic models, business definitions, relationships, rules, and actions so report and AI agents use consistent enterprise context. • Integrate enterprise data from Microsoft Fabric, APIs, lakehouse or warehouse platforms, operational systems, documents, and approved knowledge sources while maintaining security and lineage. • Validate prototypes with end users through demonstrations and structured feedback; document business outcomes, functional gaps, technical constraints, adoption considerations,and lessons learned. • Translate discovery and prototype findings into a delivery-ready backlog containing epics, capabilities, features, user stories, acceptance criteria, technical enablers, non-functional requirements, dependencies, risks, and prioritization rationale. • Define the roadmap and scalable delivery approach for expanding from the initial prototypes to an approximately 3,000-report estate, including waves, report archetypes, reusable accelerators, automation opportunities, qualitygates, and governance. • Establish development standards for React components, embedded analytics, prompts, semantic models, AI evaluation, accessibility, observability, testing, deployment, and responsible AI. • Collaborate with product owners and delivery teams on planning, estimation, release sequencing, sprint execution, demos, documentation,and knowledge transfer. • Measure outcomes such as adoption, decision-cycle improvement, report consolidation, insight quality, response accuracy, performance, and reuse of common assets.