Research Scientist Intern, Photorealistic Telepresence (phd)

Meta Meta · Big Tech · London, United Kingdom

Research Scientist Intern focused on enabling photorealistic telepresence and autonomous social agents in AR/VR. Projects involve generative AI for image/video synthesis, motion/behavior synthesis, social signal modeling, face/body reconstruction, and multimodal LLMs. Requires PhD candidate in a relevant field with experience in ML for CV/CG, deep learning frameworks, Python, and a proven publication record.

What you'd actually do

  1. Solve research problems in enabling photorealistic telepresence and autonomous social agents.
  2. Collaboration with and support of other researchers across various disciplines.
  3. Communication of research agenda, progress, and results.

Skills

Required

  • PhD in Computer Science, Computer Vision, Computer Graphics, Robotics, Machine Learning, or related field
  • Experience with solving “inverse problems” in imaging emphasizing modeling and algorithm development
  • 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
  • Must obtain work authorization in the 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 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 the completion of the internship
  • Experience working and communicating cross functionally in a team environment
  • Demonstrated software engineer experience via an internship, work experience, coding competitions, or widely used contributions in open source repositories (e.g. GitHub)
  • Experience with systems building in Python or C++
  • Experience with large-scale generative models such as LLMs and video diffusion models
  • Experience with Machine Learning for audio and visual synthesis

Nice to have

  • Experience with Computer Vision
  • Experience with Generative Model
  • Experience with Computer Graphics

What the JD emphasized

  • first-authored publications at leading conferences
  • Proven track record of achieving significant results

Other signals

  • Generative AI models for image and video synthesis
  • Motion and behavior synthesis for digital humans
  • Modeling and encoding of social signals
  • Face and body reconstruction and tracking
  • Large Foundational Models or Multimodal LLMs, such as speech-to-speech LLMs and audio-visual LLMs
  • autonomous social agents