Onsite Research Intern - Generative Video AI

Cantina; Singapore; On-site; SGD 39,000 - 50,000; Full time

Benefits offered by this job

Competitive stipend

Visa and travel support

Housing support in Singapore

Mentorship

Job summary

Cantina Labs is seeking exceptional research interns to work on the next generation of video models in Singapore for a three-month onsite internship starting Oct 2026.

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.

Qualifications

• Pursuing a PhD or final-year master's in computer science, ML, CV, or related field.
• Research experience in generative modeling, computer vision, multimodal learning, or video generation.
• Hands-on with diffusion/flow-based models, model distillation, RL, or related post-training techniques.
• Ability to formulate hypotheses, design controlled experiments, analyze results, and communicate conclusions clearly.
• Proficiency in Python and hands-on experience with PyTorch, JAX, or similar ML frameworks.
• Comfort working independently on open-ended problems while collaborating with a mentor.

Responsibilities

• Research and develop distillation methods for large-scale video generation models.
• Explore techniques to reduce inference cost while preserving quality.
• Develop reward models and optimization methods for aesthetics and temporal consistency.
• Study base-model behavior and inform model development with experimental findings.
• Design rigorous evaluations and conduct large-scale experiments on generative video models.
• Contribute to evaluation harnesses, model integrations, and research tooling.
• Document findings through research reports and presentations, with potential conference submissions.

Skills

Python

Experiment design

Research communication

Independent work

Team collaboration

Strong mathematical background

Education

PhD candidate or final-year master in CS/ML/CV

Tools

PyTorch

JAX

Diffusion models

Reinforcement learning

Job description

Cantina Labs is seeking exceptional research interns to work on the next generation of video models in Singapore for a three-month onsite internship starting Oct 2026.

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.