Research Scientist, Video Foundation Models is open at Cantina in San Francisco (hybrid). The posting gives a salary of $200K - $320K. Posted on Jun 18, 2026, and still on Cantina’s careers page when we last checked, on Nov 15, 2026.
About the role
We are building a core team to develop next-generation native video and omni foundation models for multimodal generation and understanding. Our current focus is large-scale video foundation model development, spanning pre-training, continued training, and post-training for high-quality, controllable, consistent, and efficient generation. Our broader roadmap includes reference- and memory-based generation, multimodal…
The opening lines of the posting. The rest is on Cantina’s careers page.
Hiring at Cantina
Cantina has 22 open roles right now, 6 of them remote. Most are in Engineering, Data & Research and Marketing & Community. See all its roles
