---
title: "Mario Marcolongo — AI Evaluation, Red Teaming & Information Integrity"
description: "AI Evaluation, Red Teaming & Information Integrity: Mario Marcolongo’s résumé. Italy, EU citizen, Italian and English, open to remote work and relocation."
canonical: https://mariomarcolongo.com/cv-ai
---

[Download PDF](/Mario-Marcolongo-AI-Evaluation-Red-Teaming.pdf)Print résumé

# Mario Marcolongo

AI Evaluation, Red Teaming & Information Integrity

Italy · EU citizen · Native Italian, fluent English · Open to relocation & remote work · Available now

[me@mariomarcolongo.com](mailto:me@mariomarcolongo.com) · [mariomarcolongo.com](https://mariomarcolongo.com) · [LinkedIn](https://www.linkedin.com/in/mario-marcolongo) · [ORCID](https://orcid.org/0000-0003-2846-7115) · [GitHub](https://github.com/mariomarcolongo)

## Summary

Adversarial LLM testing, including jailbreaks and prompt injection; top 5% of Gray Swan Proving Ground; member, Syntony Research Trusted Red Team Network. Paid scientific fact-checking and AI workflow configuration. Atlas preprint coauthor; merged a Basic Memory fix that stops AI agents from being told to edit or delete notes unasked.

## AI red-team competitions

### [Gray Swan](https://mariomarcolongo.com/ai-evaluation)

Independent evaluation · Final competition record, 29 October 2026

-   Top 5% of Gray Swan Proving Ground: #81, 127 recorded breaks across chat, image, agent and indirect prompt injection (13 Oct 2026).
-   49th of 390 in Lucky Break: Level Up (Oct 2026), 15 recorded breaks. Refine tests from response patterns and check recurrence across scenarios.

## Professional experience

### [Entropy for Life](https://mariomarcolongo.com/work/entropy)

Science Writer, Fact-Checker & Website Manager · Paid contractor · Jun 2023–Present · Hybrid, primarily remote · Bassano del Grappa, Italy

Client: Italian science YouTube channel · 272K subscribers (Oct 2026)

-   Research primary literature and adapt English-language evidence for Italian content; acknowledged for literature research and error detection in [Italiani veri](/work/entropy#book-acknowledgement) (Mondadori, a major European publishing group, 2025).
-   Since Oct 2026, configure Antigravity/Gemini workflows, review outputs and train the client, who used them to rename and tag thousands of images and hundreds of videos.

## Projects & public contributions

### [AI Safety Formalization Atlas](https://mariomarcolongo.com/work/atlas)

Open-source contributor & preprint coauthor · Sep 2026–Present · Remote

-   Five merged PRs: [source-metadata audit](https://github.com/mbrcic/ai-safety-formalization-atlas/pull/69), 15 citation locators, macOS validation and [agent instructions](https://github.com/mbrcic/ai-safety-formalization-atlas/blob/66ceba19c1904f00b2a734486ee0de3f5fc5a470/docs/guide/agent-instruction-design.md).
-   Coauthor, The AI Safety Formalization Atlas ([Zenodo preprint](https://doi.org/10.5281/zenodo.23088952), 2026).

### [Wikipedia, Wikidata & Wikimedia Commons](https://mariomarcolongo.com/work/wikimedia)

Public contributor · Since 2018 · Remote

-   Review citations, reconcile conflicting sources and check biomedical terminology through attributable public revisions.

## Education & credentials

### Metropolia University of Applied Sciences — Information Technology — Open UAS Path Studies

Aug 2026–Present

[Fully online degree-credit pathway](https://www.metropolia.fi/en/study-at-metropolia/open-university/path-studies/it-online) toward a BEng; self-paced coursework and assessments. Python Programming: 3 ECTS, Pass (Sep 2026).

### University of Campania Luigi Vanvitelli — Medicine coursework

2020–approx. 2023 (attendance)

[**Microsoft Applied Skills: Build an agent in Microsoft Copilot Studio**](https://learn.microsoft.com/en-us/users/mariomarcolongo/credentials/48386317f9899eb1) · Oct 2026

## Skills

**Demonstrated work:** LLM adversarial testing, jailbreaks, prompt injection, response-pattern analysis, agent instructions, technical documentation and client workflows.

**Independent investigations:** Source tracing, web archives, domain and website checks, image verification and cross-platform research; distinguish observed connections from attribution hypotheses.

**Current study:** Python, SQL, systems and quantitative foundations.

## Languages

Italian native · English fluent (EF SET C1, Mar 2024) · [Certificate](https://cert.efset.org/jHk84h)

Independent software projects use AI-assisted implementation. [Full experience and source records](/experience).