Research Scientist Intern, Perception for Digital human representation (PhD)

Meta was built to help people connect and share, and over the last decade our tools have played a critical part in changing how people around the world communicate with one another. With over a billion people using the service and more than fifty offices around the globe, a career at Meta offers countless ways to make an impact in a fast growing organization.Reality Labs (RL) teams are looking for exceptional interns to help us create next generation hyper-realistic avatars, which we call Codec Avatars. Codec Avatars allow people in different places to interact using eye contact, subtle shifts in expression, posture and gesture. This fully embodied interaction enables natural and expressive remote communication. Join a full-stack team working on computer vision, machine learning, data science, geometric and appearance modeling, physically-based modeling, sensor design and fusion. We are open to applications from those interested in the following applied research areas:- Tracking of facial expressions through machine learning computer vision and sensor fusion- Visual emotion detection via zero-shot transfer, natural language supervision, and multimodal learning- Natural language processing- Efficient deep learning (e.g., neural architecture search, sparsity, quantized networks)- Efficient and generalizable detectors for predicting keypoints, segmentations, normals, and depth- Generative AI, including LLMs, Visual-LMs, diffusion models, an other relevant techniques

• Design and execution of algorithms in the domain of computer vision, machine learning, computer graphics, sensor fusion, or natural language processing.
• Design of user studies and experiments
• Collaboration with other engineers and researchers across various disciplines
• Communication of research agenda, progress, and results

• Currently has, or is in the process of obtaining, a PhD degree in EE/CS, Applied Math or a related STEM field
• Experience in one or more of the following: computer vision (e.g. tracking, pose estimation, action/emotion recognition), computer graphics (e.g. appearance, geometry, physically-based modeling), robotics (state estimation, optimal control), machine learning (e.g. efficient deep learning, domain adaptation, transfer learning), natural language processing, or human-computer interaction
• Excellent communication skills
• High levels of creativity and problem solving capabilities
• Experience with C++ or Python
• Experience with ML frameworks such as PyTorch, Tensorflow, etc.
• Must obtain work authorization in country of employment at the time of hire, and maintain ongoing work authorization during employment

• 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.
• 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 multi-sensor streaming data processing and real-time multi-sensor, in particular cameras, fusion for computer vision and machine learning systems
• Experiences on optimizing and deploying deep learning models on SoC of mobile devices for high performance real time applications
• Experience with Machine Learning for 3D data (such as meshes, point clouds, gaussian splatting, and voxels)
• Experience with Machine Learning for Natural Language Processing and Visual Synthesis
• Experience working and communicating cross functionally in a team environment
• Intent to return to degree program after the completion of the internship/co-op