Research Scientist Intern - Post-Training (Distillation)
Is this job for you?
Build my CV Build your CV and see how well you match this role — and every other one.
The role
Advance open-source image-generation and image-editing applications by contributing to a foundational text-to-image model.
Design and implement methods to accelerate sampling in diffusion models, including re-flow, shortcut models, and adversarial diffusion distillation.
Participate in fine-tuning large-scale text-to-image models, perform ablations, and design robust evaluation metrics.
Engage in both theoretical and applied research, collaborating with ML, CV, and NLP experts.
Document results, publish findings, and contribute to open-source initiatives and external communications.
This 6-month internship is based in Paris with a hybrid office setup and is open to candidates located in Paris.
Design and implement methods to accelerate sampling in diffusion models, including re-flow, shortcut models, and adversarial diffusion distillation.
Participate in fine-tuning large-scale text-to-image models, perform ablations, and design robust evaluation metrics.
Engage in both theoretical and applied research, collaborating with ML, CV, and NLP experts.
Document results, publish findings, and contribute to open-source initiatives and external communications.
This 6-month internship is based in Paris with a hybrid office setup and is open to candidates located in Paris.
See the full job post
Responsibilities, requirements, skills and benefits — create your free account.
or
Already have an account?
Log inSimilar openings
Other roles that could suit you.