Summary
Piergiuseppe Mallozzi is an AI architect and researcher with 11 years of experience at the intersection of software engineering, machine learning, and formal verification, now based in San Francisco. He has blended academic rigor—from a PhD and postdoc at Chalmers and UC Berkeley—with hands-on product work, leading multi-agent LLM systems that integrate static analysis to automatically discover and exploit novel vulnerabilities. His projects span zero-knowledge proofs, correct-by-construction robotic mission planning, and tooling applied in NASA research, reflecting a strong background in safety-critical and security domains. As a founding engineer and independent researcher he built agentic frameworks for automated security analysis, anomaly detection, and automated patching of large codebases. Notably, he combines symbolic reasoning and formal methods with large language models to create verifiable, context-aware AI agents for cybersecurity problems. He maintains an active project portfolio online that highlights both research prizes and practical tools bridging AI and formal verification.
11 years of coding experience
9 years of employment as a software developer
Visiting PhD Student Computer Science, Visiting PhD Student Computer Science at University of California, Berkeley
Summer School Engineering, Summer School Engineering at Copenhagen University College of Engineering
Master’s Degree Computer Engineering, Master’s Degree Computer Engineering at Università di Pisa
Charles III University of Madrid (Universidad Carlos III de Madrid)
Doctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at Chalmers University of Technology
Exchange Student Computer Engineering, Exchange Student Computer Engineering at Isep - École d'ingénieurs du numérique
English, French, Spanish, Italian