Video ML Research Intern — Build Next-Gen Generative Models

Cantina, Inc.; Singapore; On-site; SGD 20,000 - 29,000; Part time

Benefits offered by this job

Visa and travel support

Housing support in Singapore

Competitive monthly stipend

Equipment and resources

Job summary

Cantina Labs in Singapore is seeking exceptional ML interns to contribute to the next generation of video models over a three-month onsite internship starting Oct 2026.

You will build data pipelines, develop reward models, conduct large-scale experiments, and contribute to evaluation harnesses while working with senior mentors.

The program offers a defined project, weekly meetings, stipend, and visa/travel housing support for eligible interns in Singapore.

Qualifications

• Pursuing a bachelor’s or master’s degree in computer science, engineering, machine learning, or a related field.
• Experience building data pipelines, ML infrastructure, or distributed systems through research, coursework, open-source contributions, or previous internships.
• 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.
• Proficient in Python and interested in building reliable systems for large-scale ML.
• Experience with video, image, audio, or other multimodal data is valuable.

Responsibilities

• Develop reward models to improve aesthetics, motion quality, temporal consistency, and prompt adherence.
• 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.
• 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 FFmpeg, PyAV, DALI, or OpenCV.
• Contribute to evaluation harnesses, model integrations, research tooling, or related projects.
• Document and communicate findings through research reports, internal presentations, and demonstrations.

Skills

Python

Data pipelines

Distributed systems

ML infrastructure

Research

Education

Bachelor’s or Master’s in CS/Engineering/ML

Tools

Ray

PySpark

Airflow

Docker

Kubernetes

Job description

Cantina Labs in Singapore is seeking exceptional ML interns to contribute to the next generation of video models over a three-month onsite internship starting Oct 2026.

You will build data pipelines, develop reward models, conduct large-scale experiments, and contribute to evaluation harnesses while working with senior mentors.

The program offers a defined project, weekly meetings, stipend, and visa/travel housing support for eligible interns in Singapore.