Job Description
We are pushing the boundaries of multimodal machine learning technology to help AI understand both visuals and sound.
The task involves reviewing and comparing short video and audio clips, with feedback directly improving the next generation of AI systems that interpret images, audio, and video.
* Review and evaluate different types of multimedia content – including audio, images, and video.
* Compare AI-generated results and choose which ones look or sound best.
* Tag or annotate videos and sounds to help train AI systems.
Become part of a pioneering project in multimodal machine learning.
Key responsibilities include:
* Evaluating multimedia content for AI training.
* Comparing AI-generated results to human evaluation standards.
* Annotating videos and sounds to enhance AI performance.
This role offers a unique opportunity to contribute to groundbreaking research in AI and multimedia analysis.
Responsibilities:
* Multimedia content evaluation.
* AIVisual and audio quality assessment.
* Data annotation and tagging.
Collaborate with top researchers to advance the field of multimodal machine learning.
In this role, you will work closely with experienced professionals in AI development and research.
Join a dynamic team dedicated to innovation and excellence in AI and multimedia analysis.
Your expertise will play a crucial role in shaping the future of AI and its applications.