jobs

Researcher, Multimodal Safety

About the TeamOpenAI is at the center of some of the highest-impact multimodal work in AI. ChatGPT serves a massive global audience, and enables diverse interactions via text, speech, and visuals. As interactive surfaces grow, models also n

In inglese

Company

OpenAI

Location

San Francisco

Status

Open

Posted

2026-08-03T17:37:24.172+00:00

OpenAI's Chat and Multimodal Safety team is hiring a researcher to make text, vision, and audio models behave safely. The work covers multimodal safety research, training and evaluation methods for vision-language models — post-training, safety evals, interventions — and collaboration with product and model teams. The posting seeks depth in VLMs, video, audio or multimodal reasoning, end-to-end knowledge from encoders to inference, and post-training experience (SFT, RL, data curation, error analysis). San Francisco, hybrid three days a week, relocation assistance offered.