Research Scientist - Video Generation

This range is provided by kadence. Your actual pay will be based on your skills and experience — talk with your recruiter to learn more.

$/yr - $/yr

Company Stage: Seed-funded AI Lab ($25M raised, Series A in progress)

Company Overview

We are a well-funded AI research lab building state-of-the-art video generation models for cinematic and creative applications. Backed by a $25M seed round and preparing for a Series A, the company has a working prototype already deployed in partnership with major movie studios
, with models actively used in upcoming feature films releasing this year
.

The mission is to push the frontier of high-fidelity, controllable, and scalable video generation
, bridging cutting-edge research with real-world production systems.

Role Overview

We are seeking a Research Scientist with deep expertise in video generation and diffusion models to join our core research team. This role offers high ownership over model architecture, training methodology, and research direction, with a direct line from research to deployment in production film pipelines.

This position is ideal for recent PhD graduates or experienced AI researchers who want their work to have both academic rigor and real-world creative impact
.

• Conduct original research in video generation, diffusion models, and generative modeling
• Design, implement, and train large-scale video diffusion models
• Improve temporal consistency, motion realism, and long-horizon coherence in generated video
• Collaborate closely with engineering and production teams to transition research into deployed systems
• Publish and present research at top-tier conferences when appropriate
• Stay current with the latest advances in generative modeling and video synthesis

• PhD in Machine Learning, Computer Vision, AI, or a related field (or equivalent research experience)
• First-author publications in video generation, diffusion models, or closely related domains
• Strong background in:
  • Diffusion models and generative modeling
  • Video representation learning and temporal modeling
  • Deep learning frameworks (e.g., PyTorch)
  • Proven ability to translate research ideas into working, scalable systems

• Experience working with large-scale video datasets
• Prior work in image/video synthesis for media, film, or creative tools
• Experience moving research into production environments
• Open-source contributions or widely cited research

• Competitive salary and meaningful equity
• Opportunity to work on models deployed in major film productions
• High-impact research role with significant technical ownership
• Collaboration with a small, elite research team
• Strong financial backing and long-term runway

• Mid-Senior level

• Full-time

• Research and Engineering

• Technology, Information and Media and Information Services

Referrals increase your chances of interviewing at kadence by 2x

We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.