Marco Gonzalez Responsible AI

Jobs 0% verified

Handshake AI – Prompt Writer / Psychological Domain Expert (

Handshake AI

Oct 2025 - Dec 2025 (3 months)

Developed psychology-grounded prompts and datasets for LLM stress-testing. Evaluated model responses for accuracy, nuance, and safety edge cases. Identified vulnerabilities in persuasion, misdiagnosis, and emotional-risk pathways. Collaborated with AI labs to refine reasoning and safety frameworks.
S

Subject Matter Expert, Adversarial Red Teaming (

Jul 2024 - Current (2 years 1 month)

Designed adversarial test suites exposing harmful, biased, or deceptive model outputs. Engineered psychologically informed jailbreaks, manipulation prompts, and obfuscation attacks. Performed reasoning, compliance, hallucination, and privacy-risk evaluations. Built behavioral threat models and safety rubrics used by engineering and policy teams. Advised on mitigations to reduce systemic risk and strengthen model alignment.
Freelance UX Researcher

Upwork

Aug 2020 - Jul 2024 (4 years)

As a Freelance UX Researcher, I led mixed-methods studies focused on user reasoning, trust, and decision-making, effectively synthesizing insights into user-risk models that informed subsequent adversarial testing work. I mapped behavioral edge cases and cognitive friction points to enhance user experience and usability. Additionally, I built comprehensive dashboards to analyze user behavior and usability metrics, ensuring data-driven decisions. My academic research skills were instrumental in conducting thorough investigations, while my benchmarking expertise allowed me to evaluate and compare user interactions effectively. Furthermore, I applied AI evaluation techniques to assess the impact of various design elements on user trust and dec

Marco Gonzalez

About

Detail

Timeline

Résumé