Senior Research Scientist - Reinforcement Learning, MoEs

This role is based in London, United Kingdom.

Responsibilities:

• Develop agent systems for real tasks in design, vision, and language.
• Scale post-training and RL across distributed systems using PyTorch.
• Contribute to the research agenda for RL/agentic systems aligned with Canva’s product goals.
• Build reward models and learning loops.
• Develop simulation tasks to identify failure modes.
• Collaborate with product and design teams to implement research findings.
• Mentor teammates and share findings with the community.

Requirements:

• Experience with reinforcement learning and mixture of expert models.
• Strong proficiency in Python and PyTorch.
• Hands-on experience with policy optimization and reward modeling.
• Experience with large-scale training and cloud multimodal tooling.