Senior Software Engineer - Video Performance - (Bay area only)

<ul><li><p>Join the team redefining how the world experiences design.</p></li></ul><p><strong>Hello, g'day, mabuhay, kia ora, 你好, hallo, vítejte!</strong></p><p>Thanks for stopping by. We know job hunting can be a little time consuming and you're probably keen to find out what's on offer, so we'll get straight to the point.</p><p>Where and how you can work</p><p>Our flagship office is in Sydney, Australia, but we've made our way from down under, to a hub in San Francisco, which is now home to our US operations. We offer flexibility in how and where you work. We trust our Canvanauts to choose the balance that empowers them and their team to achieve their goals.</p><p><strong>What you’d be doing in this role</strong></p><p>As Canva scales change continues to be part of our DNA. But we like to think that's all part of the fun. So this will give you the flavour of the type of things you'll be working on when you start, but this will likely evolve.</p><ul><li>Lead end-to-end performance strategy across the video creation lifecycle — from timeline scrubbing and real-time preview through to export and rendering. You’ll identify bottlenecks and drive measurable improvements to the editing experience.</li><li>Profile and optimize critical paths in our C++ native engine, GLSL/HLSL shaders, and ML-powered effect pipelines to reduce latency and memory footprint.</li><li>Design and build observability systems including internal profiling tools and automated regression suites that capture key performance metrics (FPS, jank, memory usage, thermal behavior) across Web, iOS, and Android.</li><li>Define and own performance metrics that directly reflect user-perceived fluidity and creative flow — ensuring performance remains a first-class product feature.</li><li>Collaborate across teams with Video Engine and AI engineers to evolve system architecture for improved parallelism, cache locality, and asynchronous processing.</li><li>Leverage hardware acceleration using platform-specific APIs (Metal, Vulkan, WebGPU) to unlock maximum performance across diverse consumer hardware.</li></ul><p><strong>You're probably a match if</strong></p><ul><li>You treat performance as a product feature. You’ve optimized complex, multi-threaded systems and can reason clearly about trade-offs between latency, memory, and maintainability.</li><li>You think in systems. You understand how frontend, backend, and native engines interact to create seamless user experiences at scale.</li><li>Strong proficiency in C++</li><li>Experience with modern systems languages (e.g., Rust) is a plus</li><li>Strong understanding of CPU/GPU architectures, memory hierarchies, and SIMD</li><li>Experience working with graphics APIs such as OpenGL, Metal, or Vulkan</li><li>You’re fluent in profiling and diagnostics. You’ve used tools such as Perf, Instruments, Chrome DevTools, Systrace, or custom telemetry systems to uncover bottlenecks and guide engineering decisions.</li><li>You understand multimedia fundamentals. You have experience with video codecs (H.264/5, VP9, AV1), container formats, and frame-accurate seeking and composition.</li><li>You use data to validate impact. You analyze telemetry at scale to identify regressions and measure improvements.</li><li>You elevate those around you. You influence peers and partner teams to prioritize performance and long-term quality.</li></ul><p><br> <u><strong>About the team</strong></u></p><p>The Video Group at Canva is redefining how millions of people tell stories. We’re a global, interdisciplinary team of rendering engineers, AI researchers, and product builders working toward ambitious goals. In San Francisco, you’ll join a high-impact team building the performant foundation that enables our creative ambitions.</p><p>We value technical excellence, thoughtful collaboration, and building systems that empower creativity for everyone.</p><p><strong>What's in it for you?</strong></p><p>Achieving our crazy big goals motivates us to work hard - and ... (truncated, view full listing at source)