Researcher, Multimodal Safety

OpenAI is at the center of some of the highest-impact multimodal work in AI. ChatGPT serves a massive global audience, enabling diverse interactions via text, speech, and visuals. As interactive surfaces grow, models need to adapt to emerging harm, understand user intent and situational context, and respond appropriately. The Chat and Multimodal Safety team ensures OpenAI's increasingly multimodal models and products behave safely across these experiences by developing research, training methods, and evaluations.

About the role

As a Researcher on the Chat and Multimodal Safety team, you will help shape how frontier models perceive and reason about the world, translating that understanding into safe behavior. We seek individuals who combine deep technical expertise with strong safety judgment, often bridging perception and language. This role is based in San Francisco, CA, with a hybrid work model of 3 days in the office per week. Relocation assistance is available.

Responsibilities

• Define and advance multimodal safety research for text, vision, and audio, connecting perception and semantic understanding to safe model behavior.
• Build training and evaluation methods for vision-language models (VLMs), including post-training, safety evaluations, and interventions to ensure models respond safely in varied contexts.
• Collaborate closely with Personal AGI, Consumer Devices, and product/model teams to translate research into safer ambient, embedded, and personalized multimodal experiences.

Qualifications

• A track record of building or advancing multimodal models, with depth in vision-language models, video understanding, image generation, audio, or multimodal reasoning—and fluency across both perception and language.
• Understanding of how multimodal systems work end-to-end, from encoders, projection layers, and modality fusion to cross-modal reasoning, scaling, and inference tradeoffs.
• Experience improving frontier model behavior through post-training, using approaches such as SFT, RL, data curation, synthetic data, evaluation, and rigorous error analysis.
• Strong research and engineering judgment for open-ended safety problems: forming testable hypotheses, designing decisive experiments, diagnosing model failures, and translating findings into robust improvements.

About OpenAI

OpenAI is an AI research and deployment company dedicated to ensuring general-purpose artificial intelligence benefits all of humanity. We push the boundaries of AI capabilities while prioritizing safety and human needs. Our mission requires valuing diverse perspectives, voices, and experiences.