Tavus15.05.2026

AI Researcher (Multimodal Audio/Video Generation)

Полная занятостьОфис

Обязанности

  • 01Lead research efforts on audio-visual generation for avatars (Neural Avatars, Talking-Heads) in conversational settings
  • 02Design models that capture and generate verbal and non-verbal signals in sync with conversation flow
  • 03Drive innovation in diffusion models, long-video generation, and audio-visual modeling
  • 04Translate research into production by collaborating with Applied ML and engineering teams
  • 05Mentor researchers, set research directions, and publish impactful work

Требования

  • 01PhD or equivalent research experience with 2–3+ years of hands‑on experience applying generative models at scale
  • 02Expertise in diffusion models and knowledge of efficiency techniques
  • 03Experience in multimodal generation spanning video, audio, and language
  • 04Proven innovation in long‑video generation and/or audio generation
  • 05Strong programming skills in PyTorch and GPU‑optimized workflows
  • 06Track record of publications in top‑tier venues such as CVPR, NeurIPS, BMVC, ICASSP
  • 07Experience leading research activities or mentoring teams

Условия

  • 01Preferred location: San Francisco (hybrid) or London (office opening soon)
  • 02Remote work considered within the U.S. or Europe for exceptional candidates