Research Intern

Speedrun Talent Network; Singapore; On-site; SGD 17,000 - 23,000; Full time

Benefits offered by this job

Visa and travel support for eligible国际

Housing support in Singapore

Research stipend

Job summary

Cantina Labs is seeking exceptional research interns to join its Singapore lab for a three-month onsite internship beginning October 2026. You will work on next-generation video models under a senior mentor, with ownership over a well-defined research or engineering problem.

Projects span post-training efficiency, reward modeling, multimodal data systems, and scalable training infrastructure. You will present findings, contribute to publications, and receive a competitive stipend with visa

Qualifications

• Pursuing a PhD or final-year Master’s in CS/ML/CV or related field.
• Hands-on experience with diffusion and flow-based video generation models.
• Experience with post-training techniques such as distillation and reinforcement learning.
• Ability to formulate hypotheses, design controlled experiments, and analyze results.
• Proficient in Python; experience with PyTorch and/or JAX is a plus.

Responsibilities

• Research and develop distillation methods for large-scale diffusion and flow-based video generation models.
• Explore techniques to reduce inference cost while maintaining or improving generation quality.
• Develop reward models and preference-based optimization to improve aesthetics and timing.
• Study how base-model behavior affects post-training outcomes and inform model development.
• Design rigorous evaluations and conduct large-scale experiments on generative video models.
• Contribute to evaluation tooling, model integrations, or product-adjacent projects.

Skills

Python

Diffusion models

Flow-based models

Reinforcement learning

Preference optimization

research experience

PyTorch

JAX

Education

PhD candidate or final-year Master’s in CS/ML/CV

Tools

PyTorch

JAX

Job description

About Cantina

Cantina Labs is a social AI company developing a suite of advanced video generation models. We bring characters to life, transforming how people tell stories, connect, and create. We build and power ecosystems. Cantina, our flagship social AI platform, is just the beginning.

About the Internship

Cantina is growing its research lab in Singapore, and we are looking for exceptional research interns to work with us on the next generation of video models in October 2026.

This is a three month onsite internship designed to give you meaningful ownership of a well-defined research or engineering problem. You will be matched with a project based on your background and interests, working closely with a senior mentor from initial problem formulation through experimentation, evaluation, and, where appropriate, submission to a leading AI conference.

Projects may focus on post-training and inference efficiency for video generation models, reward modeling and preference-based optimization multimodal data systems, or scalable infrastructure for video model training. The primary focus will be your core project, with opportunities to contribute to applied or product-adjacent work where relevant.

What You'll Work On

Depending on your project, you may:

• Research and develop distillation methods for large-scale diffusion and flow-based video generation models, including guidance and adversarial distillation

• Explore techniques that reduce inference cost while preserving or improving generation quality

• Develop reward models and preference-based optimization methods to improve aesthetics, motion quality, temporal consistency, and prompt adherence

• Study how base-model behavior affects post-training outcomes and use experimental findings to inform model development

• 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 related to your core work

• Document and communicate your findings through research reports, internal presentations, demonstrations, and potential conference submissions

You may be a good fit if you

• Are currently pursuing a PhD or are a final-year master's student in computer science, machine learning, computer vision, or a related field
• Have research experience in generative modeling, computer vision, multimodal learning, or video generation
• Have 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
• Are proficient in Python and have hands on experience with PyTorch, JAX, or another modern machine learning framework
• Are comfortable working independently on an open-ended research problem while collaborating closely with a mentor and the broader team

Experience with video, image, audio, or other multimodal data is valuable. Publications at leading venues such as NeurIPS, ICML, ICLR, CVPR, ICCV, ECCV, or AAAI are a plus, but are not required. We care most about the quality of your thinking, the depth of your technical work, and your ability to learn quickly.

What You Can Expect

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

Internship Details

• Location: Singapore
• Duration: Three months
• Working model: Onsite
• Start dates: First batch starts in October 2026, second batch starts in January 2027