Senior Research Engineer - Evaluations - Remote

Overview

Join the team redefining how the world experiences design. At Canva, our mission is to empower the world to design. We are seeking a talented Research Engineer to build our next-generation evaluation system by leveraging automatic evaluations.

In Short

• Engineer sophisticated AI agents to assess generative design models.
• Focus on building practical systems for effective research.
• Design and optimize an "MLLM-as-a-Judge" evaluation system.
• Implement inference-time alignment techniques to improve model outputs.
• Establish a benchmarking process for design-centric tasks.
• Analyze evaluation data to identify model failures and provide recommendations.
• Collaborate with research scientists and ML engineers.
• Translate research into production-ready engineering solutions.
• Work with large-scale distributed model training across GPUs.
• Utilize cloud environments, ideally AWS.

Requirements

• Strong understanding of generative AI models and their architectures.
• Experience creating data-driven evaluation methodologies.
• Experience with PyTorch and optimizing code for speed.
• Disciplined coding practices with experience in code reviews.
• Experience in cloud environments.
• Familiarity with evaluation libraries and frameworks is a plus.
• Experience with agentic AI systems is a plus.
• Knowledge of data visualization tools is a plus.
• Interest in human-computer interaction and design principles is a plus.

Benefits

• Equity packages to share in success.
• Health benefits plans for wellbeing.
• 401(k) retirement plan with company contribution.
• Inclusive parental leave policy.
• Annual Vibe & Thrive allowance for personal support.
• Flexible leave options for personal recharge.