Policy Lead for Agentic AI Safety

United States Digital Space LLC; United States; On-site; USD 140,000 - 180,000; Full time

Job summary

United States Digital Space LLC is seeking a role within its Safety Systems team to address real-world risks from model misalignment as models operate over extended horizons. You will investigate how misaligned behavior emerges across trajectories and translate insights into behavioral policies, evaluations, monitoring, and safeguards.

The position emphasizes empirical safety work, policy development, and collaboration with research, engineering, security, and product teams to balance safety

Qualifications

• Background in AI agent safety, privacy, security, or adjacent fields.
• Strong understanding of AI alignment and misaligned model behavior.
• Ability to work directly with evaluation data and identify limitations, patterns, and opportunities for deeper investigation.

Responsibilities

• Identify vulnerabilities that emerge as models interact with tools, data, and external systems, and translate them into model- and system-level safeguards.
• Develop threat models and empirical frameworks for understanding harmful outcomes from misaligned behavior.
• 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 behaviors and risks.
• Partner with research, engineering, security, and product teams to shape model and system safety, balancing safety, utility, and business risk.
• Inform deployment decisions, system cards, safeguards reports, and the company’s broader approach to agentic safety.
• Build monitoring approaches that detect regressions and emerging risks after deployment.

Job description

United States Digital Space LLC is seeking a role within its Safety Systems team to address real-world risks from model misalignment as models operate over extended horizons. You will investigate how misaligned behavior emerges across trajectories and translate insights into behavioral policies, evaluations, monitoring, and safeguards.

The position emphasizes empirical safety work, policy development, and collaboration with research, engineering, security, and product teams to balance safety