Radu Pirvu

Owned the end-to-end product vision and roadmap for Deloitte's internal GenAI assistant running on a multi-LLM platform across Azure OpenAI and GCP, with model routing based on use case complexity and data residency requirements. Defined and delivered a domain-specific RAG agent architecture — multiple purpose-built agents across regulatory compliance, document generation, and ESG frameworks, each backed by a dedicated departmental knowledge base including the firm's global institutional knowledge. Built and governed a Prompt Library of 15+ categorized, versioned prompt templates —

standardizing practitioner interactions, reducing time-to-first-useful-output, and enabling consistent quality across use cases. Led delivery of a dedicated agentic workflow tool — a multi-workflow AI application for presentation drafting, bid/RFP response, and training material generation, with template libraries and visual OCR capabilities. Implemented a Responsible AI governance framework — compliance consent, per-session client data classification controls, and data purpose-limitation enforcement — achieving zero regulatory escalations in production. Tracked real-time token consumption across GCP and Azure LLMs; partnered with Finance on capacity forecasting and budget planning to ensure predictable operational costs across development, security compliance, and platform enhancements. Monitored product health via DAU/MAU adoption metrics, per-prompt satisfaction ratings, and user feedback forms; translated data signals into sprint priorities that iteratively improved productivity outcomes for tens of thousands of practitioners.

Owned the end-to-end lifecycle of the CDP from vision and roadmap to delivery, aligning data

capabilities with personalized marketing and engagement goals.

Translated business needs into actionable data strategies, features, and integrations, enabling

customer data readiness for personalized marketing campaigns via Braze (CRM).

Partnered with engineers, vendors, and data analysts to design scalable, secure data pipelines

supporting data governance, analytics, and AI/ML-driven use cases.

Collaborated with marketing, analytics, and privacy teams to establish segmentation logic and

consent governance in line with GDPR (OneTrust).

Ensured accurate campaign measurement and attribution by maintaining clean data flows

between CDP and BI tools (Power BI, GA).

Advocated for Agile delivery practices — managing backlogs in Jira, documentation in

Confluence, and facilitating Scrum ceremonies to ensure delivery quality.

Promoted data literacy through stakeholder training, playbooks, and knowledge-sharing

documentation.

Key achievements: drove a 20% uplift in revenue per customer by integrating the CDP with

AI/ML experimentation (to automate email send time, content, and cadence)

Customer Notification System (CNS) Directed omni-channel notifications (SMS, email, in-app) for transactional and marketing use cases. Owned the product backlog and roadmap, aligning priorities with business goals, compliance, and customer needs. Collaborated with business stakeholders and development teams to balance user experience, feasibility, and scalability.

Led requirements gathering, backlog management, and user story creation, balancing user experience with technical feasibility (acceptance criteria, functional/non-functional requirements). Produced solution designs and process documentation to support implementation and knowledge sharing. Managed stakeholders and facilitated Scrum ceremonies (retro, sprint planning, daily stand-up) to ensure effective execution.