Lightricks

At our core is LTX-2, an open-source generative video model, built to deliver expressive, high-fidelity video at unmatched speed. We specialize in both research and engineering that enable efficient and scalable training and inference, allowing us to deliver state-of-the-art AI-generated video models. As a Large Scale Video Understanding Research Scientist, you will play a key role in improving video generation quality and efficiency by improving video and audio understanding pipelines used for both training data construction and model evaluation.. This role demands hands-on work with large-scale Video Language Models (VLLMs), including fine-tuning, post-training, and control, alongside implementing classic computer vision and signal processing algorithms and applying strong research skills.

At our core is LTX-2, an open-source generative video model, built to deliver expressive, high-fidelity video at unmatched speed. You'll take full creative ownership from concept to execution, a role where your ideas are trusted, your work ships at massive scale, and you'll have the freedom to experiment with new tools and approaches, including AI-powered creative platforms on a regular basis. What you will be doing Design high-quality visual and motion video ads to present Facetune to the world Create eye-catching, fresh storytelling on a daily basis Experiment with the latest AI tools on the market to elevate your workflow Own projects end-to-end, from initial concept through final delivery Maintain a strong visual identity and high design quality across all assets Brainstorm ideas and solve creative challenges with product, marketing, and performance teams Your skills and experience 2

At our core is LTX-2, an open-source generative video model, built to deliver expressive, high-fidelity video at unmatched speed. You will design and explore new use cases, train novel ways to control the generation process, and push the boundaries of generative video technology. What you will be doing Advance and extend the capabilities of our LTX-Video models through new controls, features, and use cases. Design and implement machine learning models for video, image, and audio generation, as well as multimodal applications.