Senior Research Scientist - Audio & Video AI

Location: Team Engineering

Team: Country Sydney / Australia

About the Role

Join Canva's audio-video storytelling research team within Canva Research, where we're pioneering intuitive audio tools that empower everyone to create compelling design stories. As a Senior Research Scientist - Audio & Video AI, you'll be at the heart of transforming cutting-edge machine learning into accessible design features that delight millions of Canva users worldwide. Based in our vibrant Sydney flagship campus, you'll collaborate with Research Engineers, designers, and product teams to make advanced audio storytelling as simple and magical as dragging and dropping on canvas. Your days will blend groundbreaking research with practical impact: leading audio-focused initiatives in TTS, music generation, speech enhancement, and multimodal video-audio systems; translating academic breakthroughs into Canva's design ecosystem; and optimizing models for real-time performance at scale. You'll track the latest in Diffusion Models, Transformers, and generative AI, identifying opportunities to elevate Canva's creative tools while working cross-functionally to ensure technical feasibility and user delight. Our collaborative culture thrives on curiosity, kindness, and co-creation - perfect for researchers passionate about democratizing design through AI. At Canva, we celebrate diverse backgrounds and encourage applications even if you don't tick every box. You'll enjoy equity packages, inclusive parental leave, flexible options, and our famous Vibe & Thrive allowance, all while shaping the future of design. If you're excited about making audio magic accessible to all, join our Engineering team in Sydney and help redefine how the world designs.

Key Responsibilities

• Work closely with Research Engineers on audio, video, and multimodal AI research, translating theory into practical design applications
• Determine and lead research initiatives aligned with short-term product goals and long-term strategic vision
• Turn research insights and academic breakthroughs into practical use cases for Canva's design platform
• Interpret experimental results and translate them into actionable insights for product teams
• Continually track state-of-the-art AI research and identify opportunities for Canva integration
• Design, develop, and implement innovative model architectures for audio, video, and multimodal content generation and analysis
• Optimize and scale models for efficiency, latency, and throughput across large distributed systems
• Collaborate with cross-functional stakeholders including designers, product managers, and engineers to build high-impact solutions
• Drive audio storytelling research to make advanced audio tools accessible and intuitive for all Canva users
• Mentor junior researchers and contribute to Canva's research culture through knowledge sharing

Required Qualifications

• Led the development, training, and iteration of foundational or open models based on internal research and external advancements
• Publication record or evidence of research impact in academia or industry
• Deep understanding of AI models including Diffusion Models, GANs, or Transformers with real-world application experience
• Experience adapting and fine-tuning pre-trained models for greater control and quality
• Worked successfully with large-scale AI models for audio and/or video tasks such as TTS, music generation, speech enhancement, or video-conditioned audio generation
• Proficiency in Python, PyTorch or JAX, and cloud computing platforms for efficient model training and deployment
• PhD or equivalent experience in Machine Learning, Computer Science, or related field

Preferred Qualifications

• Experience in multimodal AI combining audio, video, and design elements
• Background in design tools or creative AI applications
• Proven track record of shipping research prototypes into production systems
• Experience optimizing models for real-time inference in consumer-facing applications
• Contributions to open-source AI projects in audio/video domains

Required Skills

• Advanced machine learning research expertise
• Audio AI (TTS, music generation, speech enhancement)
• Video AI and multimodal model development
• Diffusion Models, GANs, Transformers implementation
• Model fine-tuning and optimization techniques
• Python, PyTorch/JAX proficiency
• Cloud computing and distributed systems experience
• Large-scale model training and deployment
• Experimental design and result interpretation
• Cross-functional collaboration and communication
• State-of-the-art AI literature tracking
• Creative problem-solving in design contexts
• Knowledge sharing and team mentorship
• Rapid prototyping from research to product
• Real-time inference optimization

Benefits

• Equity packages to share in Canva's success
• Inclusive parental leave policy supporting all parents and carers
• Annual Vibe & Thrive allowance for wellbeing, social connection, and office setup
• Flexible leave options empowering personal recharge and growth
• Sydney flagship campus with collaborative design-focused environment
• Regular team magic moments, connectivity, and fun activities
• Professional development opportunities in cutting-edge AI research
• Health and wellness programs supporting work-life harmony

Canva is an equal opportunity employer.