Reality Labs (RL) teams are looking for exceptional interns to help us create next generation interaction technologies for virtual and augmented reality. Join a full-stack team working on computer vision, machine learning, geometric and appearance simulation, and AI image generation. We are accepting applications from those interested in (but not limited to) the following areas: - Synthetic image generation using deep generative models, computer graphics, or physics-based simulation. - High-Fidelity image synthesis including generation of high-resolution, realistic images of eyes and face with fine details. This includes techniques to enhance appearance and geometric realism of synthetic images. - Conditional image generation based on specific conditions or constraints, such as metadata, text-based categories, image masks, or a combination of multiple input modalities. - Controllable generation of image, enabling control over generated images of eyes and face by manipulating specific attributes like style, appearance, pose, lighting, and other semantic factors. - Cross-domain image translation from one domain to another while preserving important characteristics, such as style transfer, domain adaptation, or image-to-image translation. - Few-Shot or Zero-Shot Learning: Techniques that allow models to generate images with minimal or zero examples by leveraging prior knowledge or meta-learning approaches. Our internships are twelve (12) to twenty-four (24) weeks long and we have various start dates throughout the year.
Research Scientist Intern, Synthetic Image Generation (PhD) Responsibilities
- Design and execute algorithms in the domain of computer vision, machine learning, computer graphics, and generative AI.
- Conduct in-depth literature reviews and build knowledge of the latest advancements in AI-based image generation techniques.
- Collaborate with our research team to design and implement novel algorithms for synthetic image generation or translation.
- Experiment with cutting-edge machine learning models and frameworks to enhance image synthesis capabilities.
- Analyze and evaluate model performance, iterating on approaches to improve image quality, realism, and diversity.
- Document and share research findings, contribute to technical reports, and potentially publish in academic or industry conferences/journals.
Minimum Qualifications
- Currently has, or is in the process of obtaining, a PhD degree in EE/CS, Applied Math or a related STEM field
- Experience in Python or C++
- Experience with ML frameworks such as PyTorch or Tensorflow
- Experience in one or more of the following: generative AI, computer vision, computer graphics (e.g. appearance, geometry, physically-based modeling), or machine learning (e.g. efficient deep learning, domain adaptation, transfer learning)
- Strong analytical and problem-solving skills with a passion for innovation and cutting-edge research
- Excellent written and verbal communication skills, with the ability to present complex ideas clearly and concisely
- Must obtain work authorization in country of employment at the time of hire, and maintain ongoing work authorization during employment
Preferred Qualifications
- Proven track record of achieving significant results as demonstrated by grants, fellowships, patents, or first-authored publications at leading journals or conferences such as CVPR, ECCV/ICCV, BMVC, NeurIPS, ICML, ICLR, CHI, SIGGRAPH/SIGGRAPH Asia, ICRA, IROS, RSS, TPAMI, IJCV, etc
- Contributions to open-source projects, publications, or relevant projects demonstrating expertise in synthetic image generation
- Experience with cloud computing platforms and distributed computing for large-scale experiments
- Demonstrated software engineering experience via an internship, work experience, coding competitions, or widely used contributions in open source repositories (e.g. GitHub)
- Experiences working on high volume image data processing or synthesis
