Skip to content

Research Scientist, Computer Vision (Learning From Videos)

Is this job for you?

Build your CV and see how well you match this role — and every other one.

Build my CV

The role

Lead high-impact research in video generation, spatio-temporal representation learning, world models, and multi-modal foundation models to improve dynamic scene understanding for robots.
Develop and train models on large-scale real and synthetic data, including differentiable rendering and 4D reconstruction.
Validate contributions on established benchmarks and integrate into scalable systems for robotics and autonomous driving scenarios.
Collaborate with cross-disciplinary teams and mentors, publish results at top venues, and contribute to open-source code.
Translate research into deployable algorithms and models, working with robotics and ML teams to enable world-scale autonomy.
Drive new research directions with a focus on reliability, openness, and integrity.

See the full job post

Responsibilities, requirements, skills and benefits — create your free account.

At least 6 characters. The longer, the safer.
or

Already have an account?

Similar openings

Other roles that could suit you.

See all →

Your location

Jobs and companies will be filtered on this country.

Suggested

All countries 65