Large Scale Video Understanding Research Scientist
As a Large Scale Video Understanding Research Scientist, you will enhance video generation quality and efficiency by improving video and audio understanding pipelines for training data construction and model evaluation. This role involves hands-on work with large-scale Video Language Models (VLLMs), including fine-tuning and control, as well as implementing computer vision and signal processing algorithms.
Lightricks is an AI-first company that develops next-generation content-creation technology for businesses, enterprises, and studios, aiming to bridge the gap between imagination and creation. The company's core technology is LTX-2, an open-source generative video model designed for expressive, high-fidelity video at unmatched speed, powering both its own products and a growing ecosystem of partners via API integration. Lightricks is also known globally for pioneering consumer creativity with products like Facetune, an AI-powered visual expression tool used by hundreds of millions of users worldwide. The company combines deep research, user-first design, and end-to-end execution to bring the future of expression to all.
The Core Generative AI team at Lightricks Research is a unified group of researchers and engineers focused on developing generative foundational models for LTX Studio, an AI-based video creation platform. The team's primary goal is to create a controllable, cutting-edge video generative model by integrating advanced algorithms with exceptional engineering. This involves enhancing machine learning components within a sophisticated internal training framework crucial for developing advanced models. The team specializes in research and engineering that enable efficient and scalable training and inference, delivering state-of-the-art AI-generated video models.
As a Large Scale Video Understanding Research Scientist, you will be instrumental in improving video generation quality and efficiency. This will be achieved by enhancing video and audio understanding pipelines used for both training data construction and model evaluation. The role requires hands-on experience with large-scale Video Language Models (VLLMs), including fine-tuning, post-training, and control. It also involves implementing classic computer vision and signal processing algorithms, alongside strong research skills. Expertise in post-training and controlling large-scale foundational models, understanding statistics, implementing complex systems, and debugging will be critical, especially given that video training sets comprise petabytes of data processed across hundreds to thousands of virtual machines.
This role is designed for individuals who are not only technically proficient but also deeply passionate about pushing the boundaries of AI and machine learning through innovative engineering and collaborative research.
Lightricks aims to push the boundaries of what’s possible with AI and video, focusing on the craft, the challenge, and creating genuinely new solutions. The company fosters an environment where people are encouraged to think, create, and explore, believing that real impact comes from empowerment, experimentation, evolution, and collaboration. At Lightricks, breakthroughs stem from great people and a collaborative mindset. If you seek a place that combines deep tech, creative energy, and a zero-buzzword culture, Lightricks might be the right fit.
Posted June 2, 2026