# Research Scientist, Video Foundation Models

**Company:** [Cantina](https://hotfix.jobs/companies/cantina)
**Location:** Unspecified
**Role:** AI Research
**Salary:** $200k – $320k/yr
**Skills:** Generative Modeling, Diffusion Models, Flow Matching, Dits, Video Generation, Multimodal Models, World Models, Deep Learning, Distributed Training, Model Architecture, Data Curation, Reward Modeling, Inference Systems, PyTorch
**Posted:** 2026-06-18

> Research Scientist developing large-scale native video and multimodal foundation models across architecture, training, evaluation, post-training, and inference. The role requires deep generative-modeling expertise and hands-on experience with distributed training of large-scale models.

## Job Description

## Responsibilities
- Research, develop, and scale native video and multimodal foundation models through prototyping, large-scale pre-training, continued training, and post-training.
- Explore model architectures, training objectives, and conditioning mechanisms for video generation, reference- and memory-based generation, multimodal interaction, and joint audio-video generation.
- Build and improve large-scale data curation, distributed training, evaluation, and post-training pipelines.
- Design systematic experiments covering model scaling, generation quality, controllability, consistency, robustness, and inference efficiency.
- Collaborate with researchers, engineers, and product teams to shape the technical roadmap and translate model advances into real-world capabilities.
- Contribute to research publications and open-source releases when appropriate.

## Requirements
- Strong research and engineering experience in generative modeling, including diffusion models, flow matching, DiTs, video generation, multimodal models, or world models.
- Hands-on experience training and evaluating large-scale image, video, or unified multimodal models with modern deep learning frameworks and distributed training systems.
- Track record of developing impactful models or systems through research publications, open-source contributions, production impact, or other significant technical work.
- Ability to independently own ambiguous research problems, move from ideas to experiments, and collaborate effectively.
- Specialized depth in one or more foundation-model areas, including model architecture, data curation, controllable generation, multimodal understanding and conditioning, post-training, reward modeling, model acceleration, inference systems, or deployment.

## Compensation and Benefits
- Annual base salary: $200,000–$320,000.
- Company equity.
- Medical, dental, and vision insurance with 99.99% of premiums covered.
- 42 days of paid time off, including PTO, sick days, company holidays, and floating holidays.
- Generous parental leave and fertility support.
- 401(k) retirement savings plan.
- $500/month lifestyle spending account.
- Complimentary lunch and snacks for in-office employees.
- One Medical membership.

## Similar jobs

- [Research Scientist, APEX Benchmarks](https://hotfix.jobs/jobs/77bc636d-de61-47a6-9ca0-db586f4d2d22) - Mercor - San Francisco, CA - $200k – $400k/yr
- [Research Scientist](https://hotfix.jobs/jobs/f5ff3391-4477-4eb8-b26f-78c72fc10328) - Tessera Labs - San Jose, CA - $200k – $300k/yr
- [People Research Scientist](https://hotfix.jobs/jobs/9e65a017-a0c0-4582-a774-59ce6f0c1e69) - OpenAI - San Francisco, CA - $198k – $220k/yr
- [Research Scientist – Frontier Evaluations](https://hotfix.jobs/jobs/7f457896-ca9c-4429-82a4-fd6190219c60) - AfterQuery - San Francisco, CA - $210k – $450k/yr
- [Software Engineer (Gen AI)](https://hotfix.jobs/jobs/7af58525-5b44-47cc-a964-4a0eee5a3506) - Earnin - Mountain View, CA - $181k – $222k/yr

**Apply:** https://hotfix.jobs/jobs/740cde0d-5c2d-4410-a691-8f90f1ee2fd9
**Canonical:** https://hotfix.jobs/jobs/740cde0d-5c2d-4410-a691-8f90f1ee2fd9