Research Scientist, Generative AI/Video (San Francisco)

About sync.

sync. is a team of artists, engineers, and scientists building foundation models to edit and modify people in video. Founded by the creators of Wav2lip and backed by legendary investors, including YC, Google, and visionaries Nat Friedman and Daniel Gross, we've raised 6 million dollars in our seed round to evolve how we create and consume media.

Within months of launch our flagship lipsync API scaled to millions in revenue and powers video translation, dubbing, and dialogue replacement workflows for thousands of editors, developers, and businesses around the world.

That's only the beginning, we're building a creative suite to give anyone Photoshop-like control over humans in video – zero-shot understanding and fine-grained editing of expressions, gestures, movement, identity, and more.

Everyone has a story to tell, but not everyone's a storyteller – yet. We're looking for talented and driven individuals from all backgrounds to build inspired tools that amplify human creativity.

About the role

We're looking for an exceptional Research Scientist to help us build generative video models that understand and modify humans in video. You'll work directly with the creators of Wav2lip, pushing the boundaries of what's possible in fine-grained video control and video understanding.

What you'll work on

1. Design and scale cutting-edge generative models that can seamlessly control and edit different attributes of humans in video
2. Pioneer new architectures for zero-shot video representation learning
3. Explore novel problems and capabilities to push the limits of what is possible
4. Tackle core challenges in precise video editing that large generative models struggle with
5. Build primitives that capture and express human idiosyncrasies

What you'll need

1. 3+ years research experience in generative AI, computer vision, or deep learning
2. Deep expertise in training generative models in PyTorch
3. Curiosity and the drive to understand the unknown
4. Proven record of implementing and adapting cutting-edge papers
5. Proven ability to take research from concept to production
6. Track record of breakthrough technical innovation

Preferred qualifications

1. Expertise in recent SOTA generative architectures (e.g. Diffusion)
2. History working with face/human editing in video
3. Notable publications or open-source contributions
4. Expertise in model optimization and scalability

Our goal is to keep the team lean, hungry, and shipping fast.

These are the qualities we embody and look for:

1. Raw intelligence: we tackle complex problems and push the boundaries of what's possible.
2. Boundless curiosity: we're always learning, exploring new technologies, and questioning assumptions.
3. Exceptional resolve: we persevere through challenges and never lose sight of our goals.
4. High agency: we take ownership of our work and drive initiatives forward autonomously.
5. Outlier hustle: we work smart and hard, going above and beyond to achieve extraordinary results.
6. Obsessively data-driven: we base our decisions on solid data and measurable outcomes.
7. Radical candor: we communicate openly and honestly, providing direct feedback to help each other grow.