Member of Technical Staff, Video Data & Model Evaluation

About the role

Cantina, a social AI company building real-time models that bring characters to life, is hiring a Member of Technical Staff to join its growing Singapore research team. You will own the data and evaluation strategies behind its video generation models, working with research scientists, machine learning engineers, product teams and external data partners.

Key responsibilities

• Define quality standards for video generation across aesthetics, realism, composition, motion, temporal consistency, instruction following, subject consistency, editing preservation and text rendering.
• Evaluate model iterations, analyse failure patterns and turn findings into data, training and prompting strategies.
• Own end-to-end training data projects, from sourcing and construction through annotation, captioning, quality control and delivery.
• Develop labeling systems and annotation/captioning standards, and evaluate synthetic-data workflows.
• Build automated annotation and filtering workflows using vision-language models, system prompts and quality-scoring models.
• Design structured model evaluation processes, including test-set design, criteria, failure attribution and reporting, and link them to data strategy.
• Train and calibrate annotation teams and partners, run quality audits and improve delivery standards.
• Partner with research, engineering, product and creative teams on data initiatives and future model capabilities.

Required profile

• Experience in data strategy, dataset development, annotation or model evaluation for generative image, video or multimodal models.
• Experience supporting model development across continued training, supervised fine-tuning, post-training or evaluation.
• Strong understanding of generative media tasks such as image and video generation, multimodal generation and instruction-based editing.
• Experience developing labeling taxonomies, annotation guidelines, captioning standards, quality thresholds and evaluation frameworks.
• Experience managing large-scale data-production or annotation projects and collaborating with research, engineering, creative and partner teams.

Required skills

• Strong visual judgment and the ability to turn subjective quality expectations into measurable standards.
• Familiarity with automated captioning, synthetic-data generation, vision-language models, prompt design, Python, SQL or other data and workflow automation tools is a plus.

What we offer

• Competitive salary and company equity.
• Personal time off and paid holidays.
• Health insurance and global travel insurance.
• Monthly spending stipend of $500 (~S$635).
• All equipment needed for a home office.