Model Policy Manager, Multimodal Safety
ABOUT THE TEAM
Safety Systems manages the complete lifecycle of safety efforts for OpenAI’s frontier models, ensuring our models are deployed responsibly and have a positive impact on society. Our work spans diverse research and engineering initiatives—from system-level safeguards and model training to evaluation and red-teaming—all aimed at mitigating misuse, misalignment, and maintaining our high bar for safety. We lead OpenAI's commitment to developing and deploying safe Artificial General Intelligence (AGI), fostering a culture of trust, responsibility, and transparency. Our goal is to continuously learn from deployments, distribute AI’s benefits widely, and ensure that powerful tools remain aligned with human values and safety considerations.
Within Safety Systems, the Model Policy team works to ensure that frontier models behave safely and reliably in real-world environments by designing policies that define safe model behavior. Our relevant publications include:
- Safety at every step https://openai.com/safety/
- OpenAI GPT6 System Card https://deploymentsafety.openai.com/gpt-6-astra
- OpenAI Model Spec https://openai.com/index/introducing-the-model-spec/
- GPT-Live https://openai.com/index/introducing-gpt-live/
- ChatGPT Images 2.5 https://openai.com/index/introducing-chatgpt-images-2-5/
ABOUT THE ROLE
We are hiring a Model Policy Manager to focus on the safety of multimodal models. In this role, you will shape how OpenAI identifies, evaluates, and addresses risks in multimodal AI models - such as GPT-Live https://openai.com/index/introducing-gpt-live/ and ChatGPT Images https://openai.com/index/introducing-chatgpt-images-2-0/ - as well as multimodal capabilities in frontier AI models.
This role is based in San Francisco, CA. We use a hybrid work model of 3 days in the office per week and offer relocation assistance to new employees.
IN THIS ROLE, YOU WILL:
- Design and maintain model policies for audio, image, video, and omni-modal behavior.
- Translate theories of harm and threat models into behavioral safety policies, evaluation criteria, grading guidance, and safeguards.
- Identify and analyze safety regressions and failure patterns to identify gaps in existing policies and inform policy iteration.
- Develop policy artifacts that support model training, evaluation, and deployment, including behavior instructions, human-data campaigns, golden sets, and evaluations.
- Partner with AI researchers, domain experts, and product teams to operationalize policy into measurable model behavior.
YOU MIGHT THRIVE IN THIS ROLE IF YOU:
- Have strong judgment about the real-world risks of advanced multimodal AI systems.
- Possess experience turning ambiguous safety questions into clear data-driven policies, behavioral boundaries, and measurable evaluation criteria.
- Treat policy as an end-to-end, measurable system by testing whether it produces the intended model behavior and diagnosing gaps across policy, data, graders, and safeguards.
- Leverage strong technical judgement to design policies around model behavior that can realistically be trained, measured, and supervised at scale.
- Demonstrate strong technical fluency and uses AI tools to accelerate policy development, evaluate model behavior, analyze failure patterns, and turn findings into actionable improvements.
- Are 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.
- Enjoy fast-paced, collaborative research environments where priorities shift as models, evidence, and risks change.
- Take a pragmatic, evidence-driven approach to reducing risk while preserving beneficial uses of AI.
- Have hands-on experience driving consensus and action in ambiguous spaces.