Research Scientist – Video Generation (Singapore)

About the role

Cantina Labs is a social AI company developing real‑time models that bring characters to life. Cantina is expanding and seeks a Research Scientist to join its Singapore team, driving foundational research on video generation models and translating findings into durable model improvements.

Key responsibilities

• Build and maintain scalable systems for ingesting, preprocessing, and delivering large‑scale video data for model training.
• Design and scale distributed data pipelines for dataset generation and repeated 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.
• Optimize cloud‑based data storage and movement across AWS, GCS, or Azure for cost and efficiency.
• Develop distillation methods for large‑scale diffusion and flow‑based video generation models, focusing on quality and inference cost.
• Develop reward models and preference‑based fine‑tuning pipelines aligning video generation with human judgments.
• Analyze base model behavior and collaborate with foundation model team to inform pretraining decisions.

Required profile

• 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 like Airflow.
• Familiarity with containerization and orchestration, including Docker and Kubernetes.
• Experience with cloud‑based data storage and compute (AWS, GCS, Azure) and associated trade‑offs.
• Knowledge of video and media processing tools such as FFmpeg, PyAV, DALI, or OpenCV.
• Research background in post‑training methods for large‑scale diffusion or flow‑based generative models, including distillation.
• Experience with reward modeling or preference‑based fine‑tuning (RLHF, DPO) for generative models.
• Proficiency in Python and modern ML frameworks, preferably PyTorch or JAX.

Required skills

• Python
• PyTorch
• JAX
• PySpark
• Ray
• Airflow
• Docker
• Kubernetes
• AWS
• Google Cloud Storage
• Azure
• FFmpeg
• PyAV
• DALI
• OpenCV

What we offer

• Competitive salary and generous company equity.
• Personal time off and paid holidays.
• Health insurance and global travel insurance.
• Monthly spending stipend of $500 (≈S$635).
• Equipment provision for home office.