Video/Image AI Research Lead

At Viva Labs, we believe videos are the best way to communicate with the world in the age of AI. Our flagship product, VivaChat, enables users to chat with AI-generated personalities.

We are a team of engineers and AI experts, including alumni from Meta, Microsoft, Skydio, and Harvard. We enjoy shipping code, creating humorous videos, and sharing good food. Our company culture is built on experimentation and openness.

About the Role:

• We’re looking for early members to join our research team. You’ll work closely with the founders and take ownership of key technical decisions related to building and productionizing state-of-the-art computer vision models for images and videos.

Ideal Experiences:

• Experience training generative models from scratch (Gans, NERFs, Gaussian Splatting, and diffusion models)
• 4+ years experience training state of the art models
• Proficiency in Python and deep learning frameworks (e.g., PyTorch, TensorFlow, JAX)
• Track record showing independent ownership of entire research projects from start to finish
• A love of image and videos (since you’ll be spending an inordinate amount of time with them)

Nice to Have:

• PhD or relevant publications in conferences
• Prior Experiences Training models doing Lip syncing, facial re-enactment, body motion

Investors:

We’re funded by top investors like YCombinator, 8VC, Good News Ventures, and notable angels from top AI companies like Suno.ai.