AI Video Research Engineer Intern(m/w/x)

Description

You will push the boundaries of digital finance by refining multimodal foundation models, from architecture design to large-scale training, while contributing to high-impact research publications.

Requirements

• •MSc or PhD candidate in Computer Science, Machine Learning, Computer Vision, or related field
• •Research topic or experience in image/video generation or multimodal learning
• •Awareness of open-source video foundation models and limitations
• •Proficiency with PyTorch and modern deep learning workflows
• •Strong analytical thinking, creativity, and collaboration skills
• •Prior first-author publications in CVPR, ICCV, ECCV, NeurIPS, or ICLR
• •Demonstrated research codebase or benchmarks on GitHub or similar
• •Experience with large-scale or distributed training
• •Experience with diffusion-based, transformer-based, or hybrid video models

Tasks

• •Research open-source video foundation models
• •Improve multimodal video generation models
• •Design model architectures and evaluations
• •Execute pre-training and supervised fine-tuning
• •Manage post-training and inference processes
• •Benchmark models against state-of-the-art standards
• •Identify bottlenecks and propose novel improvements
• •Handle large-scale video datasets
• •Utilize distributed training systems
• •Collaborate on high-potential research publications

Tools & Technologies

Benefits