$ cat jobs/engineering-manager-ml-evaluation-platform-canva-4042f0558013.json
Engineering Manager - (ML) - Evaluation Platform
Join the team redefining how the world experiences design. Hey, g'day! 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. Where and how you can work Our offices are a hub for collaboration and energy. But we also believe in working where you do your best thinking. Canva offers flexibility to work in a way that suits you, whether that's remote, hybrid, or in-office. This role is based in Sydney, close to the majority of the Engineering team. About the Group/Team Canva's AI Platform Group provides the foundational infrastructure and tooling that powers AI features across the company, supporting MLEs, researchers, and AI builders from CORE and the wider organisation. Within the group, the Evaluation Platform team owns the end-to-end evaluation lifecycle: test-like evals integrated into developer workflows, the Arena comparative evaluation service, monitoring evals sampled from production traffic, and human labelling tooling. The team partners closely with AI feature teams, CORE researchers, and adjacent platform teams (Inference, Datasets, and Training) to make rigorous evaluation the default for every AI feature Canva ships. About the Role/Specialty We're seeking an engineering manager who can lead a large, senior team through a period of consolidation and growth. The Evaluation Platform team operates at the intersection of ML research practice and production platform engineering; you'll need enough technical depth in ML and evaluation to hold a credible strategic position, and the people leadership skills to coach a team of 9+ engineers, most of them senior. The role involves significant stakeholder complexity: multiple internal customer teams with competing priorities, adjacent teams with overlapping ambitions in the evaluation space, and a company-wide programme of work that runs through this team. You'll be expected to own and articulate the evaluatio