Research Intern

The role

Research interns will work on the next generation of video models. You will work on a well-defined research or engineering problem with a senior mentor through experimentation, evaluation, and potential conference submission.

What you will do

• Research and develop distillation methods for large-scale diffusion and flow-based video generation models
• Explore techniques that reduce inference cost while preserving or improving generation quality
• Develop reward models and preference-based optimization methods
• Study how base-model behavior affects post-training outcomes
• Design rigorous evaluations and conduct large-scale experiments on generative video models
• Contribute to evaluation harnesses, model integrations, research tooling, or other product-adjacent projects
• Document and communicate findings through research reports, internal presentations, demonstrations, and potential conference submissions

Required qualifications

• Currently pursuing a PhD or are a final-year master’s student in computer science, machine learning, computer vision, or a related field
• Research experience in generative modeling, computer vision, multimodal learning, or video generation
• Hands on experience with diffusion models, flow-based models, model distillation, reinforcement learning, preference optimization, or related post-training techniques
• Can formulate hypotheses, design controlled experiments, analyze results, and communicate conclusions clearly
• Proficient in Python
• Hands-on experience with PyTorch, JAX, or another modern machine learning framework
• Comfortable working independently on an open-ended research problem while collaborating closely with a mentor and the broader team

Nice to have

• Experience with video, image, audio, or other multimodal data
• Publications at leading venues such as NeurIPS, ICML, ICLR, CVPR, ICCV, ECCV, or AAAI

Benefits

• A defined project and named senior mentor
• Weekly one-on-one meetings and clear project milestones
• Meaningful compute allocation
• First-author positioning by default where contribution supports a publication
• Timely internal review of research intended for submission
• Support for conference travel if paper is accepted
• Opportunities to demonstrate work and receive credit for product contributions
• Competitive monthly stipend
• Visa and travel support for eligible international candidates
• Housing support for qualifying international interns in Singapore
• Equipment and resources

About the company

Cantina Labs is a social AI company developing a suite of advanced video generation models. Their flagship social AI platform is Cantina.