Cantina Labs
social AI
ResearchScientist
Neural analysis suggests this role is
optimal for Mid candidates.
“Research Scientist at Cantina Labs. Skills: foundational research on video generation models, post-training research, large-scale data systems or pipelines for machine learning workflows, distributed data pipelines, workflow orchestration, containerized pipeline infrastructure, cloud-based data storage and compute optimization, deduplication workflows, distillation methods for large-scale diffusion and flow-based video generation models, reward modeling and preference-based fine-tuning pipelines”
What You'll Achieve.
translate research findings into durable model improvements; preserving or improving generation quality while reducing inference cost; align video generation quality with human judgments across dimensions such as aesthetics, motion quality, and prompt adherence; inform pretraining decisions accordingly
Industry & Context.
Analyze the relationship between base model behavior and post-training outcomes
What They're Looking For.
Must Have
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, Experience with 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, research background in post-training methods for large-scale diffusion or flow-based generative models, 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, Solid understanding of the interplay between pretraining and post-training, and how base model properties affect distillation and fine-tuning outcomes, Proficiency in Python, Proficiency in modern machine learning frameworks
Nice to Have
Publications at top-tier venues (NeurIPS, ICML, ICLR, CVPR, ICCV, ECCV) preferred, preference for PyTorch or JAX
What You'll Do.
drive foundational research on video generation models
taking ownership across the full research cycle
driving post-training research
collaborate closely with data
and adjacent modeling teams to translate research findings into durable model improvements
Build and maintain scalable systems for ingesting
and delivering large-scale video data for model training
Design and scale distributed data pipelines for preprocessing
and repeated dataset refreshes
Own workflow orchestration
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 (AWS
and operational efficiency
Define and implement best practices for dataset storage layout
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
Analyze the relationship between base model behavior and post-training outcomes
and work with the foundation model team to inform pretraining decisions accordingly
How You'll Work.
Team & Collaboration
collaborate closely with data, infrastructure, and adjacent modeling teams
Process & Methodology
Track record of independent research, with the ability to drive projects from initial idea through experimental validation
Full Job Description
About Cantina: Cantina Labs is a social AI company, developing a suite of advanced real-time models that push the boundaries of expression, personality, and realism. We bring characters to life, transforming how people tell stories, connect, and create. We build and power ecosystems. Cantina, our flagship social AI platform, is just the beginning. About the Role: Cantina is expanding, and we're looking for a Research Scientist to join our growing Singapore team! In this role, you will drive foundational research on video generation models, taking ownership across the full research cycle and driving post-training research. Furthermore, you'll collaborate closely with data, infrastructure, and adjacent modeling teams 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 (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 genera
Applying for this Research Scientist role?
Most applicants get filtered before a human reads their resume. See if yours makes the cut.
How to Apply on Ashby
- Ashby is a fast modern ATS — most applications take under 3 minutes.
- The resume parser is strong; verify parsed experience dates and job titles.
- Custom screening questions are often scored algorithmically — answer completely.
- Location field affects geo-based screening; use your actual metro area.
ANONYMOUS · UNFILTERED
What do employees actually say about Cantina Labs?
Real rants from real employees. Read before you apply.