Research Scientist – Audiovisual Generation, Model Foundations

<h2>Who we are</h2> <p>Lightricks is an AI-first company creating next-generation content-creation technology for businesses, enterprises, and studios, with a mission to bridge the gap between imagination and creation. At our core is LTX-2, an open-source generative video model, built to deliver expressive, high-fidelity video at unmatched speed. It powers both our own products and a growing ecosystem of partners through API integration.</p> <p>The company is also known globally for pioneering consumer creativity through products like Facetune, one of the world’s most recognized creative brands, which helped introduce AI-powered visual expression to hundreds of millions of users worldwide. We combine deep research, user-first design, and end-to-end execution from concept to final render, to bring the future of expression to all.</p> <h2>The role&nbsp;</h2> <p>Following the success of LTX-2, our widely adopted open-source text-to-audio+video model, we are expanding our efforts to develop cutting-edge audio+video generation models and are hiring Research Scientists to join our LTX-2 Core team.</p> <p>At Lightricks, we’ve been at the forefront of innovation in text-to-image and text-to-audio+video generation, with LTX-2 driving our flagship product, LTX Studio, and gaining significant traction in the research and open-source communities, including integrations with platforms like ComfyUI and Diffusers.</p> <p>This role focuses on pioneering model architecture and pre-training algorithms, shaping the next generation of our foundational generative AI models.</p> <h2>What you will be doing</h2> <ul> <li>Pre-train and fine-tune video, audio, and image generative models to pursue state-of-the-art results.</li> <li>Publish papers and open source models to benefit the research community and advance the field<strong>.</strong></li> <li>Design and implement machine learning models for text-to-audio and text-to-video generation.</li> <li>Collaborate with data engineers to curate and preprocess text and video data.</li> <li>Optimize models for high performance, ensuring efficient training and inference.</li> <li>Build new controls and capabilities into generative text-to-audio and text-to-video models.</li> <li>Stay updated with the latest developments in Generative AI, particularly in the fields of image, video, and audio.</li> <li>Work closely with product teams to integrate AI models into applications and services.</li> <li>Conduct experiments and prototype new concepts to advance the capabilities of our AI tools.</li> </ul> <h2>Your skills and experience</h2> <ul> <li>Track record of coming up with new ideas or improving upon existing ideas in generative AI, demonstrated by accomplishments such as first-author publications or projects.</li> <li>Excellence in engineering as well as research with strong programming skills in Python, and deep familiarity with machine learning frameworks.</li> <li>Experience in training large diffusion transformer models from scratch.</li> <li>Proven track record of handling large-scale datasets to train neural networks effectively.</li> <li>PhD or equivalent experience in the field of generative AI - a plus.</li> </ul> <h2>We got you covered</h2> <ul> <li>We run daily door-to-door shuttles, offering Car-to-go subscriptions from several locations in central Israel, plus free parking and train-station pickups.</li> <li>We’re proud to have 2 chef-led restaurants on site by the legendary Machneyuda Group (yes, that Machneyuda!), plus a bakery nestled in the heart of our office, filled daily with the scent of fresh pastries.</li> <li>We empower employees with cutting-edge tools and learning opportunities to grow and succeed through workshops, access and training on platforms, subscriptions, and clear guidelines for responsible AI use.</li> <li>&nbsp;</li> </ul>