Agentic RL Researcher – Distributed Computing

Huawei Canada has an immediate permanent opening for a Researcher in the Distributed Data Storage and Management Lab, focusing on advanced research in distributed data systems. The role involves designing and developing algorithms for reinforcement learning and multi-agent systems, optimizing performance on distributed compute clusters, and collaborating on the deployment of scalable learning systems.

Responsibilities:

• Design and develop advanced Agentic Reinforcement Learning (RL) and Multi-Agent Reinforcement Learning (MARL) algorithms for cooperative, competitive, and mixed-agent environments, including CTDE, decentralized learning, and hierarchical agent systems
• Build scalable simulation and training platforms for large-scale agent systems, supporting self-play, population-based training, curriculum learning, and emergent behavior analysis
• Optimize multi-agent learning performance on distributed compute clusters, improving sample efficiency, credit assignment, agent coordination, communication learning, and training stability
• Research and prototype new approaches for multi-agent intelligence, including communication protocols, credit assignment, game-theoretic learning dynamics, meta-learning, and adaptive agent populations
• Translate cutting-edge research in agentic AI and MARL into production-ready systems for real-world or high-fidelity simulated environments
• Develop benchmarking frameworks and evaluation metrics for agent coordination, robustness, scalability, and safety
• Collaborate with research, infrastructure, and product teams to deploy scalable agentic learning systems in real-world applications
• Contribute to technical leadership and innovation through publications, patents, open-source contributions, and conference presentations