Research Scientist Intern, Photorealistic Telepresence (PhD)
About The Position
Meta is seeking exceptional research interns to advance photorealistic telepresence and create next-generation embodied agents through human understanding and synthesis using vision-language models (VLMs), large language models (LLMs), and video models. The work spans artificial intelligence, computer vision, and computer graphics, with research regularly published at leading conferences and journals. Potential projects include VLMs and LLMs for human understanding; generative image and video models for photorealistic XR telepresence and embodied agents; motion and behavior synthesis for digital humans and embodied agents; speech-to-speech and audio-visual LLMs for natural multimodal interaction; and face and body reconstruction, tracking, and encoding of social signals for XR. Internships last 12 to 24 weeks, with various start dates throughout the year.
Requirements
- Currently have, or be in the process of obtaining, a PhD in Computer Science, Computer Vision, Computer Graphics, Robotics, Machine Learning, or a related field.
- Experience solving inverse problems in imaging, emphasizing modeling and algorithm development.
- At least 2 years of experience with machine learning for solving computer vision and computer graphics problems.
- Experience with deep learning frameworks such as PyTorch and TensorBoard.
- Experience with scientific programming languages such as Python.
- Obtain work authorization in the country of employment at the time of hire and maintain ongoing work authorization during employment.
Nice To Haves
- Proven track record of significant results demonstrated by patents and first-authored publications at leading workshops or conferences such as ICCV, CVPR, NeurIPS, SIGGRAPH, ICASSP, or similar.
- Intent to return to a degree program after completing the internship.
- Experience working and communicating cross-functionally in a team environment.
- Demonstrated software engineering experience through an internship, work experience, coding competitions, or widely used open-source contributions (e.g., GitHub).
- Experience building systems in Python or C++.
- Experience with large-scale generative models such as VLMs, LLMs, and image or video diffusion models.
- Experience with machine learning for 3D data, such as meshes, point clouds, Gaussian splatting, and voxels.
- Experience with machine learning for audio and visual synthesis.
Responsibilities
- Solve research problems in enabling photorealistic telepresence and embodied agents.
- Collaborate with and support other researchers across various disciplines.
- Communicate research agenda, progress, and results.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Intern
Education Level
Ph.D. or professional degree
