Trusted Red Team Network

• Conduct project-based adversarial evaluations that directly inform governance and mitigation decisions.
• Perform specialist testing in ML security, prompt engineering, policy analysis, geopolitical forecasting, or systems thinking.
• Collaborate across disciplines on scoped engagements with defined threat models and evidence requirements.
• Translate technical findings into actionable controls and oversight artifacts.

This role directly informs governance and mitigation decisions for AI systems, helping to ensure safe and responsible deployment of advanced technologies.

• Expertise in ML security, prompt engineering, policy analysis, geopolitical forecasting, or systems thinking.
• Ability to conduct adversarial evaluations and translate findings into actionable controls.
• Experience collaborating across disciplines on scoped engagements.

Compensation and benefits are not specified in the posting.

Syntony is an organization focused on AI safety and governance, engaging experts to perform adversarial evaluations that drive real mitigation and oversight decisions.