Senior RL Scientist, Multimodal Agent Systems

Canva; Greater London; Hybrid; GBP 70,000 - 100,000; Full time

Job summary

A leading design platform in Greater London is seeking a Senior Research Scientist to advance their work on reinforcement learning and agentic systems. You will drive research initiatives and participate in the development of innovative solutions that enhance product experiences. This position demands deep expertise in reinforcement learning, Python, and teamwork across multiple domains. The role offers a flexible work environment supported by a variety of benefits designed to foster success and well-being.

Benefits

Equity packages

Inclusive parental leave policy

Annual Vibe & Thrive allowance

Flexible leave options

Qualifications

• Depth in implementing and post-training of LLMs/VLMs/Diffusion models.
• Experience modifying and adapting open-source models.
• Strong experience with experimental design including reproducibility.
• Hands-on experience with policy optimization and reward modeling.

Responsibilities

• Develop agent systems for real tasks in design, vision, and language.
• Scale post-training and RL across distributed systems.
• Contribute to the research agenda for RL/agentic systems.
• Build reward models and learning loops for reinforcement learning.

Skills

Reinforcement Learning

Python

Post-training

Experimental Design

PyTorch

Tools

Distributed Training

ML Codebases

Job description

A leading design platform in Greater London is seeking a Senior Research Scientist to advance their work on reinforcement learning and agentic systems. You will drive research initiatives and participate in the development of innovative solutions that enhance product experiences. This position demands deep expertise in reinforcement learning, Python, and teamwork across multiple domains. The role offers a flexible work environment supported by a variety of benefits designed to foster success and well-being.