Model Policy Manager, Agentic Safety
OpenAI · San Francisco
About this role
## About the Team **Our Safety Systems** (https://openai.com/safety/safety-systems) is at the forefront of OpenAI’s mission to build and deploy safe AGI—driving AI safety and fostering a culture of trust and transparency. Within Safety Systems, the **Model Policy** team ensures increasingly capable models behave safely and reliably in real-world environments. The team investigates emerging model failures, defines the behavior models should exhibit instead, and develops the data, evaluations, monitoring, and safeguards needed to improve and validate that behavior. ## About the Role In this role, you will shape how OpenAI understands and addresses real-world risks that emerge from **model misalignment** as models become more autonomous and operate over longer horizons. You’ll investigate how misaligned behavior emerges across extended trajectories—such as when models persist toward the wrong objective, take unsafe shortcuts, lose track of instructions, exploit weaknesses in their environment, or circumvent constraints—and translate those insights into **behavioral policies, evaluations, monitoring, and safeguards**. This role is ideal if you want to turn alignment and safety concerns into concrete, empirically grounded improvements to frontier AI systems. ## 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 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 trade-offs between safety, utility, and business risk. - Inform deployment decisions, system cards, safeguards reports, and OpenAI’s broader approach to agentic safety. - Build monitoring approaches that detect regressions and emerging risks after deployment. ## What We’re Seeking - Strong background in **AI agent safety, privacy, security, cybersecurity**, or adjacent fields, with an adversarial mindset to investigate real-world harmful outcomes. - Demonstrated interest in AI alignment and strong understanding of the technical drivers of misaligned model behavior. - Technical fluency to work directly with evaluation and training data, interpret what the data shows, and identify limitations, patterns, and opportunities for deeper investigation. - Comfort working hands-on with model data and evaluation results (inspecting examples, analyzing failure patterns, assessing data quality, and distinguishing policy failures from grader/model/system failures). - Uses empirical evidence to develop and refine safety policies and safeguards. - Can translate complex/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. ## Re
Listing freshness
CronJobs last confirmed this listing 1h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.