Research Scientist • Intern

Who you are

You are a PhD candidate with a strong background in computer vision and machine learning — your research has focused on synthetic image generation and you are familiar with deep generative models. You have experience in high-fidelity image synthesis, particularly in generating realistic images of eyes and faces with fine details. Your understanding of conditional image generation allows you to work with various input modalities, including metadata and image masks.

You possess knowledge of controllable image generation techniques, enabling you to manipulate attributes like style, appearance, and lighting in generated images. You are also well-versed in cross-domain image translation, applying techniques such as style transfer and domain adaptation. Your familiarity with few-shot and zero-shot learning techniques demonstrates your ability to leverage prior knowledge for image generation with minimal examples.

What you'll do

As a Research Scientist Intern at Meta, you will join a full-stack team dedicated to creating innovative interaction technologies for virtual and augmented reality. You will collaborate with experienced researchers and engineers to develop and enhance synthetic image generation techniques. Your work will involve applying deep learning models to generate high-resolution images, focusing on enhancing both geometric and appearance realism.

You will engage in projects that require conditional image generation, where you will explore how to generate images based on specific constraints and conditions. Your role will also include experimenting with controllable generation methods, allowing you to manipulate various attributes of the images you create. You will contribute to cross-domain image translation projects, ensuring that important characteristics are preserved during the transformation process.

Throughout your internship, you will have the opportunity to apply your knowledge of few-shot and zero-shot learning, working on models that can generate images with minimal training data. You will collaborate closely with your team to push the boundaries of what is possible in synthetic image generation, contributing to the development of next-generation technologies that enhance user experiences in virtual and augmented reality.

What we offer

Meta provides a dynamic and innovative environment where you can grow your skills and contribute to cutting-edge projects. This internship lasts between twelve to twenty-four weeks, with various start dates throughout the year. You will have the chance to work alongside some of the brightest minds in the industry, gaining valuable experience in a fast-evolving field. We encourage you to apply even if your experience doesn't match every requirement, as we value diverse perspectives and backgrounds.