Research Scientist

The role

You will drive foundational research on video generation models and drive post-training research. You will collaborate with data, infrastructure, and modeling teams to translate research findings into model improvements.

What you will 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 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
• Research and develop distillation methods for large-scale diffusion and flow-based video generation models
• Develop reward models and preference-based fine-tuning pipelines
• Analyze the relationship between base model behavior and post-training outcomes

Required qualifications

• 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 (AWS, GCS, and/or Azure)
• 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
• Experience with reward modeling or preference-based fine-tuning for generative models, including RLHF, DPO or equivalent alignment approaches
• Solid understanding of the interplay between pretraining and post-training
• Proficiency in Python and modern machine learning frameworks
• Track record of independent research, with the ability to drive projects from initial idea through experimental validation
• 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 (NeurIPS, ICML, ICLR, CVPR, ICCV, ECCV)
• Strong preference for PyTorch or JAX

Benefits

• Competitive salary
• Generous company equity
• Personal time off
• Paid holidays
• Health insurance
• Global travel insurance
• Monthly spending stipend: $500 (~S$635)
• Equipment: All equipment needed for your home office

About the company

Cantina Labs is a social AI company, developing a suite of advanced real-time models that push the boundaries of expression, personality, and realism. They build and power ecosystems.