Machine Learning Intern

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.

Cantina is growing its research lab in Singapore, and we are looking for exceptional machine learning 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.

Depending on your project, you may:

• Develop reward models 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

• Build systems for ingesting, preprocessing, curating, and delivering large-scale video datasets

• Develop distributed pipelines for dataset generation, deduplication, preprocessing, and repeated dataset refreshes

• Improve the reliability, reproducibility, and efficiency of data and model-training workflows

• Build tooling for video and multimodal data using technologies such as FFmpeg, PyAV, DALI, or OpenCV

• 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

• Are pursuing a bachelor’s or master’s degree in computer science, engineering, machine learning, or a related field

• Have experience building data pipelines, ML infrastructure, or distributed systems through research, coursework, open-source contributions, or previous internships

• Are familiar with tools such as Ray, PySpark, Airflow, Docker, Kubernetes, or equivalent technologies

• Have worked with cloud storage or compute platforms such as AWS, Google Cloud, or Azure

• Understand practical considerations around data throughput, storage layout, caching, monitoring, and failure recovery

• Are proficient in Python and interested in building reliable systems for large-scale machine learning

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.

• 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

• Location: Singapore

• Duration: Three months

• Working model: Onsite

• Start dates: Start dates: First batch starts in October 2026; second batch starts in January 2027