Senior Research Scientist - Audio & Video AI

Canva Canva · Enterprise · Sydney, Australia · Information Technology

Senior Research Scientist role focused on audio-video storytelling research, developing and integrating cutting-edge AI technologies for audio, video, and multimodal content generation and analysis. The role involves leading research initiatives, translating insights into practical applications, optimizing models, and collaborating with cross-functional teams to enhance user experiences and drive product innovation.

What you'd actually do

  1. Working closely with Research Engineers on research in audio, video and multimodal AI, with a focus on audio, translating theory into practical applications
  2. Determining and leading research initiatives aligned with short-term product goals and longer-term strategic goals
  3. Turning research insights and academic breakthroughs into practical use cases and advancing those findings
  4. Interpreting experimental results and translating them into actionable insights
  5. Continually tracking the state-of-the-art and identifying opportunities to incorporate new technologies into our research

Skills

Required

  • Python
  • PyTorch or Jax
  • cloud computing platforms
  • Diffusion Models
  • GANs
  • Transformers
  • TTS
  • music generation
  • speech enhancement
  • video conditioned audio generation

Nice to have

  • audio research
  • video research
  • multimodal AI
  • model architectures
  • model optimization
  • model control
  • model quality

What the JD emphasized

  • publication record
  • large-scale AI models for audio and/or video tasks

Other signals

  • audio research
  • video research
  • multimodal AI
  • model architectures
  • model optimization