Research Scientist Intern, Video & Image Generation (PhD) at Meta

Zurich, Zurich, Switzerland -

Full Time

Start Date

Immediate

Expiry Date

26 Feb, 26

Salary

0.0

Posted On

28 Nov, 25

Experience

0 year(s) or above

Remote Job

Yes

Telecommute

Yes

Sponsor Visa

Skills

Computer Vision, Generative Modeling, Machine Learning, Deep Learning, Programming, Algorithm Design, Model Evaluation, Multimodal Learning, Generative Diffusion, Transformer Architectures, Spatio-Temporal Modeling, Collaboration, Research, Large-Scale Datasets, PyTorch, TensorFlow

Industry

Software Development

Description

The XR Tech Research team is seeking highly motivated Research Interns to join us in advancing the next generation of video and image generation technologies. Our team is dedicated to conducting foundational, state-of-the-art research in video generation, with a strong focus on pushing the scientific and technical boundaries of generative AI to enable future immersive and interactive experiences. As a Research Intern, you will work alongside leading experts in computer vision, generative modeling, and multimodal learning, contributing to projects at the frontier of large-scale video and image generation models. Our work not only advances the academic field but also lays the groundwork for future XR systems and applications, shaping how people will interact, create, and connect in virtual and real-world environments. About the Team The XR Tech Research team has a long-standing history of groundbreaking contributions to generative AI research across modalities—from images and video to 3D and beyond. We are at the forefront of advancing foundational video generation models, collaborating with world-class research groups, and driving the next wave of innovation in immersive technologies. Our work is both academically impactful and tightly connected to real-world applications, enabling breakthroughs that redefine the future of XR. Responsibilities Conduct research on advanced topics in video and image generation, including but not limited to generative diffusion and transformer architectures, spatio-temporal modeling, and multimodal integration. Design, implement, and evaluate novel algorithms and model architectures. Collaborate closely with researchers and engineers across the XR-Tech group and broader FAIR/GenAI teams. Present findings and share insights that help shape both ongoing research and future directions. Minimum Qualifications Currently pursuing a PhD in Computer Science, Electrical Engineering, or related field with a focus on machine learning, computer vision, or generative modeling Strong research background with publications (or submissions) in top conferences such as CVPR, NeurIPS, ICLR, ICCV, ICML, or SIGGRAPH Proficiency in deep learning frameworks such as PyTorch or TensorFlow Solid understanding of generative models (diffusion models, GANs, VAEs, autoregressive transformers, etc.) Strong programming skills and ability to work with large-scale datasets and compute infrastructure Must obtain work authorization in the country of employment at the time of hire, and maintain ongoing work authorization during employment Preferred Qualifications Research experience in video generation, temporal modeling, or multimodal learning Strong track record of contributions to open-source projects, benchmarks, or shared research artifacts Demonstrated ability to work collaboratively in interdisciplinary research environments

Responsibilities

Conduct research on advanced topics in video and image generation and design, implement, and evaluate novel algorithms and model architectures. Collaborate closely with researchers and engineers across the XR-Tech group and present findings to shape ongoing research.