Model Policy Manager, Agentic Safety

United States Digital Space LLC; United States; Hybrid; 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

About the Team

Our Safety Systems team is at the forefront of the company's mission to build and deploy safe AGI, driving our commitment to AI safety and fostering a culture of trust and transparency.

Within Safety Systems, the Model Policy team works to ensure that increasingly capable models behave safely and reliably in real-world environments. We investigate emerging model failures, define the behavior models should exhibit instead, and develop the data, evaluations, monitoring, and safeguards needed to improve and validate that behavior. Our work connects alignment research with the practical challenges of training and deploying frontier models.

About the Role

In this role, you will shape how the company understands and addresses real-world risks that emerge from model misalignment as models become more autonomous and operate over longer horizons. You will investigate how misaligned behavior emerges across extended trajectories - including when models persist toward the wrong objective, take unsafe shortcuts, lose track of instructions, exploit weaknesses in their environment, or circumvent constraints - and translate these insights into behavioral policies, evaluations, monitoring, and safeguards. This role is ideal for someone who wants to turn alignment and safety concerns into concrete, empirically grounded improvements to frontier AI systems.

Your 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 difficult trade-offs between 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.

We’re seeking someone who:

• Brings a strong background in AI agent safety, privacy, security, cybersecurity, or adjacent fields, with the adversarial mindset needed to investigate real-world harmful outcomes.

• Has demonstrated interest in AI alignment and a strong understanding of the technical drivers of misaligned model behavior.

• Has enough technical fluency to work directly with evaluation and training data, understand what the data is showing, and identify limitations, patterns, and opportunities for deeper investigation.

• Is comfortable working hands-on with model data and evaluation results, including inspecting examples, analyzing failure patterns, assessing data quality, and distinguishing policy failures from grader, model, or system failures.

• Uses empirical evidence to develop and refine safety policies and safeguards.

• Can translate complex or ambiguous alignment risks into precise behavioral expectations and measurable evaluation criteria.

• Works effectively across research, engineering, security, product, and policy.

• Communicates clearly about complex and uncertain technical risks.

• Enjoys fast-paced, collaborative research environments where priorities shift as models, evidence, and risks change.

Our relevant publications:

• Safety and alignment in an era of long-horizon models

• Accelerating the cyber defense ecosystem that protects us all

• Safety at every step

• the company GPT5.6 System Card

• the company Model Spec

Workplace & Location

This role is based in our San Francisco office. We do encourage you to apply even if you prefer a different work location as factors may change over time.

We offer relocation support to new employees, and we use a hybrid model: three days in the office per week with optional work from home on Thursdays and Fridays.

Our open-plan offices have height-adjustable desks, conference rooms, phone booths, well-stocked kitchens full of snacks and drinks, three in-house prepared meals daily, a private outdoor space for working in the sun or socializing, nap rooms, private bike storage, and more.

About the company

the company is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity. We push the boundaries of the capabilities of AI systems and seek to safely deploy them to the world through our products. AI is an extremely powerful tool that must be created with safety and human needs at its core, and to achieve our mission, we must encompass and value the many different perspectives, voices, and experiences that form the full spectrum of humanity.

We are an equal opportunity employer, and we do not discriminate on the basis of race, religion, color, national origin, sex, sexual orientation, age, veteran status, disability, genetic information, or other applicable legally protected characteristic.

For additional information, please see the company’s Aff…

Background checks for applicants will be administered in accordance with applicable law, and qualified applicants with arrest or conviction records will be considered for employment consistent with those laws, including the San Francisco Fair Chance Ordinance, the Los Angeles County Fair Chance Ordinance for Employers, and the California Fair Chance Act, for US-based candidates. For unincorporated Los Angeles County workers: we reasonably believe that criminal history may have a direct, adverse and negative relationship with the following job duties, potentially resulting in the withdrawal of a conditional offer of employment: protect computer hardware entrusted to you from theft, loss or damage; return all computer hardware in your possession (including the data contained therein) upon termination of employment or end of assignment; and maintain the confidentiality of proprietary, confidential, and non-public information. In addition, job duties require access to secure and protected information technology systems and related data security obligations.

At the company, we believe artificial intelligence has the potential to help people solve immense global challenges, and we want the upside of AI to be widely shared. Join us in shaping the future of technology.