Location: Bay Area (Hybrid)
Compensation: $250K–$290K + Equity
We’re hiring on behalf of a fast-growing, well-funded Bay Area startup redefining video creation using generative AI. Their platform enables video-to-video generation — combining diffusion models, Gaussian splatting, and human-centric 3D rendering.
In this role, you’ll:
- Research and deploy models for video generation, in-painting & 3D simulation
- Work on human-centric modeling (pose, movement, reenactment)
- Build on top of diffusion models, transformers, and neural rendering methods
- Collaborate with a multidisciplinary team of researchers, engineers & artists
- A PhD (or equivalent) in AI, CV, or graphics
- Publications in top venues (CVPR, NeurIPS, ICCV, SIGGRAPH, etc.)
- Strong experience with generative models or visual computing