<h3>Company Description</h3>Join the team redefining how the world experiences design.Hey, hello, gday, mabuhay, kia ora, 你好, hallo, vítejte!Thanks for stopping by. We know job hunting can be a little time consuming and youre probably keen to find out whats on offer, so well get straight to the point.Where and how you can workOur flagship office is in Sydney, Australia, but weve 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.<h3>Job Description</h3>At Canva, our mission is to empower the world to design. To ensure our generative AI models are truly helpful, we are seeking a talented Research Engineer to build our next-generation evaluation system by leveraging automatic evaluations.About the role:You will engineer sophisticated AI agents that can automatically assess the quality and human alignment of our generative design models. This high-impact role focuses on building the practical systems that make cutting-edge research effective, to provide a rapid feedback loop that guides the future of design generation at Canva, ultimately empowering millions of users to create.At the moment, this role is focused on:<ul><li>Agentic Evaluation Systems: Engineering autonomous AI agents that use Multimodal Large Language Models (MLLMs) to evaluate the quality, relevance, and human alignment of generated designs.</li><li>Inference-Time Alignment: Mastering techniques that improve model outputs without full retraining, but by inference-based methods including prompt engineering, in-context learning and Retrieval-Augmented Generation (RAG).</li><li>Model Benchmarking &amp; Analysis: Building a rigorous framework to systematically benchmark internal and external quality understanding models, delivering clear, data-driven insights on human alignment.</li></ul>Primary Responsibilities:<ul><li>Design, build, and optimize the infrastructure for an MLLM-as-a-Judge evaluation system for scalable, automated feedback.</li><li>Implement and experiment with inference-time alignment techniques (Prompt Engineering, RAG, ICL) to directly improve model output quality.</li><li>Establish and manage a comprehensive benchmarking process to compare various foundation models on design-centric tasks.</li><li>Analyze evaluation data to identify model failure modes and provide actionable recommendations to the research team.</li><li>Collaborate with research scientists and ML engineers to integrate the agentic judge system into the model development lifecycle.</li><li>Translate the latest research in LLM evaluation and agentic AI into practical, production-ready engineering solutions.</li></ul>You’re probably a match if you:<ul><li>You have a strong understanding of generative AI models (e.g., Diffusion Models, GANs, Transformers) and their architectures, with practical experience that informs robust evaluation strategies</li><li>Excel at creating data-driven evaluation methodologies, turning user analytics into clear, actionable insights.</li><li>You’ve successfully managed or optimized large-scale distributed model training across hundreds of GPUs</li><li>You have a solid understanding of machine learning, have worked with PyTorch and know how to optimize such codes for speed</li><li>You have disciplined coding practices, and are experienced with code reviews and pull requests.</li><li>You have experience working in cloud environments, ideally AWS</li></ul>Nice to Have:<ul><li>Familiarity with evaluation libraries and frameworks.</li><li>Experience building or working with agentic AI systems or multi-agent coordination.</li><li>Knowledge of data visualization tools to communicate findings effectively.</li><li>A background or interest in human-computer interaction, design principles.</li></ul><h3>Qualifications</h3><h3>Additional Information</h3>Whats in it for you?Achieving our crazy big goals motivates us to work hard - and we do - but youll 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.Heres a taste of whats on offer:<ul><li>Equity packages - we want our success to be yours too</li><li>Health benefits plans to support you and your wellbeing</li><li>401(k) retirement plan with company contribution</li><li>Inclusive parental leave policy that supports all parents &amp; carers</li><li>An annual Vibe &amp; Thrive allowance to support your wellbeing, social connection, office setup &amp; more</li><li>Flexible leave options that empower you to be a force for good, take time to recharge and supports you personally</li></ul>Check out <a href="https://lifeatcanva.com/">lifeatcanva.com</a> for more information.Other stuff to knowWe make hiring decisions based on your experience, skills and passion, as well as how you can enhance Canva and our culture. When you apply, please tell us the pronouns you use and any reasonable adjustments you may need during the interview process.   At Canva, we value fairness, and we strive to provide competitive, market-informed compensation whilst ensuring internal equity within the team in each region. We make hiring decisions based on your skills, experience and our overall assessment of what we observed and learnt in the hiring process. The target base salary range for this position is $220,000 - $280,000. When calculating offers, we make salary decisions based on market data, your experience levels, and internal benchmarks of your peers in the same domain and job level.Please note that interviews are predominantly conducted virtually.