Startups · AI

Model Policy Manager, Multimodal Safety

OpenAI · San Francisco · On-site

← All jobs
About OpenAI

Backed by Greylock, Insight and Khosla.

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 and ChatGPT Images - 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.

More about this role

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

OpenAI GPT6 System Card

OpenAI Model Spec

GPT-Live

ChatGPT Images 2.5

We are hiring a Model Policy Manager to focus on the safety of multimodal models. In this role, you will shape how OpenAI identifies,...

Read the full posting on OpenAI's site ↗

Safety Systems

Build your edge while you search

Free tools for founders and investors, plus VC Unfiltered, our take on startups, venture and the people who build them.