Specialized Application CV

Trust, Safety & Knowledge Integrity Specialist

This is the concise document to send for this role family. The master CV is a comprehensive evidence archive; it is normally not attached unless requested.

AI Safety CVAll application CVsMaster CV

Mario Marcolongo

Trust, Safety & Knowledge Integrity Specialist

Open-source research · source provenance · content integrity · structured-data verification · adversarial analysis

Italy · EU work authorization · Open to worldwide relocation and international B2B contractingmariomarcolongo.com[email protected]LinkedInGitHub

Knowledge-integrity and open-source research specialist with eight years of auditable Wikimedia work, paid scientific verification across 59+ Entropy for Life projects inside a 267K-subscriber science-communication brand, and self-directed adversarial testing of AI systems. The 26 July 2026 Gray Swan snapshot displayed rank #75 (top 6%) and 110 Proving Ground total breaks.

Selected evidence

8 yearsPublic source-work recordWikipedia, Wikidata and Wikimedia Commons
4,317Auditable contributionsClaims, citations, metadata and media records
110Platform-displayed Proving Ground breaks#75 · top 6% · four evaluation surfaces
59+Scientific projects checked55+ YouTube projects · 4 articles

Relevant experience

Scientific Contributor & Structured-Data Editor

Wikipedia, Wikidata & Wikimedia Commons
Public contribution record ↗Integrity work samples ↗
Mar 2018 — Present
  • Check claims and citations, reconcile conflicting public sources, improve structured metadata and document provenance across public knowledge projects.
  • Prepare bilingual descriptions, rights information and source context for openly licensed media, including VRT-verified material supplied directly by original authors.
  • Maintain a fully inspectable public activity record while separating aggregate contribution counts from claims about the quality of any individual edit.

Scientific Research, Fact-Checking & Website Operations Contractor

Entropy for Life · Independent contractor
Author page ↗H5N1 tracker ↗
Jun 2023 — Present
  • Investigate scientific and health claims through primary-literature searches, source-quality comparison and cross-source corroboration.
  • Co-authored a continuously updated H5N1 situation tracker, reconciling fast-changing epidemiological reports and documenting source dates.
  • Communicate uncertainty, conflicting evidence and corrections to a public-facing content team without overstating conclusions.
Trust, Safety & Knowledge Integrity SpecialistPage 1 of 2

Additional relevant experience

Model-Behavior Evaluator

Independent practice · Gray Swan Proving Ground
Evaluation record ↗Dated evidence ↗Public profile ↗
Jul 2026 — Present
  • Test instruction hierarchy, policy boundaries, indirect prompt injection and agentic tool-use behavior across repeated adversarial scenarios.
  • Reached #75 on the Proving Ground (top 6%) with 110 platform-displayed total breaks in the 26 July 2026 snapshot.
  • Apply threat-oriented thinking and evidence capture to ambiguous behavior without claiming application-security or penetration-testing expertise.

Additional evidence

Precision-first research-integrity tooling

MDPI Filter applies exact DOI, domain and public-identifier evidence across browser and Zotero workflows, prioritizing false-positive avoidance, local checks and explicit network controls.

Capabilities

Open-source researchAdvanced web and scholarly search, public-record triangulation, archival comparison, source provenance and cross-source corroboration
Knowledge integrityClaim decomposition, citation checking, entity reconciliation, structured metadata, rights context and evidence-bound reporting
Trust & safety analysisContent-risk thinking, ambiguous-case investigation, taxonomy development, policy-boundary testing and escalation-ready documentation
AI adversarial analysisPrompt and jailbreak analysis, indirect prompt injection, multi-turn behavior, multimodal inputs and agentic tool-use testing
CommunicationConcise investigative writing, uncertainty communication, reproducibility notes and explanations for technical and non-technical audiences

Best-fit role families

  • Trust & safety and content-integrity operations
  • Knowledge integrity and public-record investigations
  • OSINT research and source-provenance analysis
  • AI abuse, policy and adversarial-analysis support

Credentials & language

  • GALENOS Crowd Evidence Synthesis Training — Cochrane Crowd & GALENOS, 2026
  • Career Essentials in Generative AI — Microsoft & LinkedIn, 2024
  • EF SET English Certificate — 68/100, C1 overall, 2024
  • Italian — native. English — C1 overall (EF SET 68/100); advanced technical reading and professional/technical writing.
Mario Marcolongo · [email protected]Page 2 of 2