Model Policy Manager, Agentic Safety

📋 Description

• Identify vulnerabilities that emerge as models interact with tools, data, and external systems, and
• Develop threat models and empirical frameworks for understanding harmful outcomes from misaligned
• Build frameworks for understanding harmful outcomes arising from model misalignment.
• Identify the underlying behaviors and system conditions that drive those outcomes.
• Turn findings into policy frameworks, evaluation criteria, online measurement and safeguards.
• Develop human data campaigns and gold sets to ground measurement and evaluation of emerging

🎯 Requirements

• Brings a strong background in AI agent safety, privacy, security, cybersecurity, or adjacent
• Has demonstrated interest in AI alignment and a strong understanding of the technical drivers of
• Has enough technical fluency to work directly with evaluation and training data, understand what
• Is comfortable working hands-on with model data and evaluation results, including inspecting
• Uses empirical evidence to develop and refine safety policies and safeguards.
• Can translate complex or ambiguous alignment risks into precise behavioral expectations and

🎁 Benefits

• Offers Equity
• Relocation support
• Hybrid work model (3 days in office, optional work from home on Thursdays and Fridays)
• Open-plan offices with height-adjustable desks, conference rooms, phone booths, well-stocked