Research Scientist

As a Research Scientist at Cantina Labs, you will drive foundational research on video generation models, taking ownership across the full research cycle and post-training research. You'll collaborate closely with data, infrastructure, and adjacent modeling teams in our Singapore office to translate research findings into durable model improvements.

What you'll do

• Build and maintain scalable systems for ingesting, preprocessing, and delivering large-scale video data for model training
• Design and scale distributed data pipelines for preprocessing, dataset generation, and repeated dataset refreshes
• Own workflow orchestration, job scheduling, monitoring, and failure recovery for large-scale data processing jobs
• Implement and maintain containerized pipeline infrastructure using Kubernetes or equivalent orchestration systems
• Optimize cloud-based data storage and movement across providers such as AWS, GCS, or Azure for cost, throughput, and operational efficiency
• Define and implement best practices for dataset storage layout, versioning, caching, retention, and access patterns
• Build tooling to support deduplication workflows at scale, including near-dedup pipelines over large video corpora
• Research and develop distillation methods for large-scale diffusion and flow-based video generation models, including guidance distillation and adversarial distillation, with a focus on preserving or improving generation quality while reducing inference cost
• Develop reward models and preference-based fine-tuning pipelines that align video generation quality with human judgments across dimensions such as aesthetics, motion quality, and prompt adherence
• Analyze the relationship between base model behavior and post-training outcomes, and work with the foundation model team to inform pretraining decisions accordingly

What you bring

• Strong hands-on experience building or scaling large-scale data systems or pipelines for machine learning workflows
• Experience with distributed data processing frameworks such as PySpark or Ray, and orchestration tools such as Airflow or equivalent
• Familiarity with containerization and container orchestration, including Docker and Kubernetes
• Experience working with cloud-based data storage and compute including AWS, GCS, and/or Azure, including tradeoffs around cost, throughput, storage layout, and access patterns
• Familiarity with video and media processing tools such as FFmpeg, PyAV, DALI, or OpenCV
• Familiarity with multimodal or media data, including video, image, text, and audio
• Strong research background in post-training methods for large-scale diffusion or flow-based generative models, with deep hands-on experience in distillation across both inference efficiency and quality preservation
• Experience with reward modeling or preference-based fine-tuning for generative models, including RLHF, DPO or equivalent alignment approaches
• A solid understanding of the interplay between pretraining and post-training, and how base model properties affect distillation and fine-tuning outcomes
• Proficiency in Python and modern machine learning frameworks, with a strong preference for PyTorch or JAX
• A track record of independent research, with the ability to drive projects from initial idea through experimental validation
• A good understanding of the practical challenges involved in building reliable, scalable, and reproducible data workflows for machine learning systems

Nice to have

• Publications at top-tier venues such as NeurIPS, ICML, ICLR, CVPR, ICCV, or ECCV

What we offer

• Competitive salary and generous company equity
• Personal time off and paid holidays
• Health insurance
• Global travel insurance covering international travel
• Monthly spending stipend of $500 (approximately S$635)
• All equipment needed for your home office

About Cantina Labs

Cantina Labs is a social AI company developing advanced real-time models for video generation and character creation. The flagship platform, Cantina, enables people to tell stories, connect, and create through AI-powered ecosystems.