Patricia Montecchiarini

I’m a Product Engineer who embeds directly with enterprise clients, identifies the real blocker behind the stated problem, and translates complex regulatory and technical requirements into production deployments—owning outcomes end-to-end. In my current role, I designed and deployed a self-hosted LLM environment on AWS EC2, built security automation (Dependabot monitoring, AI-assisted code auditing, and automated PR review via GitHub Actions), and recommended and shipped a service architecture spanning persona generation, data storage, analytics, and the client app.

I also lead governance work that holds up in regulated environments: I conducted a GDPR Article 17 compliance audit from scratch with full data lineage mapping and defined automated deletion/anonymization protocols, architected an internal RBAC mesh enforcing least-privilege security across tools, and authored my company’s AI usage policy and SaaS governance framework. Before this, I was a Senior Frontend Developer at Endava and ran freelance web projects, and I started my career as a Civil Litigation Attorney—where my risk-assessment methodology now directly informs how I design AI governance protocols and engineering operations.