About the job
About the Role and Team
As a Multimodal Research Engineer at Character. AI, you'll play a pivotal role in pioneering advanced video and image generation models, breathing life into AI characters in innovative ways. Your contributions will significantly influence the daily interactions of millions of users, enhancing their experiences with rich and engaging AI visuals.
The Multimodal team specializes in the training, fine-tuning, and deployment of state-of-the-art image, audio, and video generation models that enhance Character. AI's visual interactions. We oversee the entire model lifecycle, encompassing data pipelines, training processes, deployment, and product integration.
In this role, you will lead our video model training initiatives, focusing on joint audio-visual generation and transforming images into captivating videos. Collaborating with cross-functional teams in research, product development, and infrastructure, you will explore the frontiers of AI-generated visual content at scale.
