
About the Group/Team We're the Discovery group, part of Canva's Content & Discovery supergroup. Our mission is to enable every user to effortlessly find content that empowers them to design. Within the group, the Private Search Quality team owns helping users find their own personal, team, and branded content — the search experience people rely on every time they go looking for something they've already made or been given access to. About the Role/Specialty As a Machine Learning Engineer on Private Search Quality, you'll work on the ranking and relevance systems behind how Canva surfaces private, team, and brand content. That means building and improving ML ranking models and lifting relevance for all users, and helping the team's search results hold up as usage patterns and content types keep expanding, including newer surfaces like agent-driven search. It also means working with our Backend Engineers with our ElasticSearch and Vector Search databases. You'll take ownership of scoped projects end-to-end, from problem framing through to shipped, measurable impact on search quality. There is a strong emphasis on experimentation and iterating on learnings to get the best outcomes for our users. What you’ll do (responsibilities) Build, evaluate, and improve ML ranking models for private, team, and brand content search Drive relevance and recall improvements, with a particular focus on enterprise user outcomes Work on intelligent result understanding, search recovery, and exact title match to help users navigate results Contribute to indexing with a variety of technologies including ElasticSeach/OpenSearch, Vector search and annotation Extend private and brand search quality and coverage into newer surfaces like agent search Investigate and resolve quality or relevance regressions in production search Communicate technical trade-offs clearly, including to non-technical stakeholders, and share knowledge across the team What we're looking for: You've got hands-on experience building and shipping ML systems in production, ideally in search, ranking, LTR or relevance, not just training models in a notebook. You're comfortable defining and moving the metrics that matter (relevance, recall, ranking quality) rather than just chasing model accuracy in isolation. You can take a scoped project from idea to shipped with minimal guidance, bringing your own judgement to how a problem should be solved rather than needing a fully defined solution handed to you. You're highly autonomous, comfortable with ambiguity as search surfaces and user needs evolve, and you want your work to show up in something real people use every day. What You'll Learn & Build Deep experience building and improving production ranking and relevance systems at Canva's scale Exposure to how ML, product, and infra decisions intersect across the wider Discovery group The chance to work on emerging surfaces like agent-driven search as the space develops
Don't tick all the boxes? Don't worry about that - nobody does! We’d still love to hear from you! At Canva, we know that great engineers come from a variety of backgrounds, and we value passion, curiosity, and a willingness to learn just as much as specific experience. If you're excited about this role but don’t tick every box, we encourage you to apply, you might a great fit in ways you didn’t expect! What's in it for you? Achieving our crazy big goals motivates us to work hard - and we do - but you'll experience lots of moments of magic, connectivity and fun woven throughout life at Canva, too. We also offer a stack of benefits to set you up for every success in and outside of work. Here's a taste of what's on offer: Equity packages - we want our success to be yours too Inclusive parental leave policy that supports all parents & carers An annual Vibe & Thrive allowance to support your wellbeing, social connection, office setup & more Flexible leave options that empower you to be a force for good, take time to recharge and s
Every tech & IT company hiring across India — with AI match scores — on one live map.
Open the map →