Research Scientist - Intern Position - LTX Video at Lightricks

Jerusalem, Jerusalem District, Israel -

Full Time

Start Date

Immediate

Expiry Date

10 Jan, 26

Salary

0.0

Posted On

12 Oct, 25

Experience

0 year(s) or above

Remote Job

Yes

Telecommute

Yes

Sponsor Visa

Skills

Generative AI, Machine Learning, Python, Model Architecture, Pre-training Algorithms, Data Engineering, Video Generation, Image Generation, Large-scale Datasets, Diffusion Transformer Models, Research Publications, AI Integration, Experimentation, Prototyping, Text-to-Video Generation, Performance Optimization

Industry

Software Development

Description

Lightricks, an AI-first company, is revolutionizing how visual content is created. With a mission to bridge the gap between imagination and creation, through AI technology, we bring cutting-edge products to the creative and business spaces. Our advanced AI photo and video generation models, including our open-source LTXV model, power our apps and platforms: Facetune, LTX Studio, LTX Scaler, Photoleap, and Videoleap, enabling creators and brands to leverage the latest research breakthroughs, offering endless control over their creative potential. Our influencer marketing platforms, Popular Pays, provide influencers with the ability to scale their content and monetize their work, while offering brands opportunities to expand their reach through tailored creator partnerships. The role Following the success of LTX-Video, our widely adopted open-source text-to-video model, we are expanding our efforts to develop cutting-edge video generation models and are hiring Research Scientists to join our LTX-Video Core team. At Lightricks, we’ve been at the forefront of innovation in text-to-image and text-to-video generation, with LTX-Video 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. This role focuses on pioneering model architecture and pre-training algorithms, shaping the next generation of our foundational generative AI models. What you will be doing Pre-train and fine-tune video and image generative models to pursue state-of-the-art results. Publish papers and open-source models to benefit the research community and advance the field. Design and implement machine learning models for text-to-video generation. Collaborate with data engineers to curate and preprocess text and video data. Optimize models for high performance, ensuring efficiency in training and inference phases. Build new controls and capabilities into generative text-to-video models. Stay updated with the latest developments in Generative AI, particularly in the fields of image, video, and audio. Work closely with product teams to integrate AI models into applications and services. Conduct experiments and prototype new concepts to advance the capabilities of our AI tools. Your skills and experience Currently pursuing a Master's or PhD degree in the field of Generative AI 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. Excellence in engineering as well as research with strong programming skills in Python, and deep familiarity with machine learning frameworks. Experience in training large diffusion transformer models from scratch. Proven track record of handling large-scale datasets to train neural networks effectively.

Responsibilities

The role involves pre-training and fine-tuning video and image generative models, as well as publishing papers and open-source models. You will collaborate with data engineers and product teams to optimize models and integrate AI into applications.