Location
toronto, on, Canada
Posted
June 27, 2026
Job Description
Drive innovation in AI at Preference Model as a Reinforcement Learning Engineer focused on low-level tasks. This role requires strong skills in C/C++, Python, and systems engineering for impactful contributions in a collaborative environment.
You will be instrumental in designing and implementing low-level reinforcement learning environments, addressing real-world challenges faced by frontier models. By building efficient scoring systems and developing kernel tasks, your work will ensure that AI models can interact effectively with complex hardware and achieve meaningful breakthroughs.
Key Responsibilities:
• Develop kernel-focused RL environments to challenge models effectively
• Identify and design environments that emphasize niche hardware utilization
• Structure scoring methods that prevent manipulation by models
• Innovate and support hardware-focused projects
• Scale tasks to maximize training efficiency
Requirements:
• Expertise in C / C++ / CUDA with ...
You will be instrumental in designing and implementing low-level reinforcement learning environments, addressing real-world challenges faced by frontier models. By building efficient scoring systems and developing kernel tasks, your work will ensure that AI models can interact effectively with complex hardware and achieve meaningful breakthroughs.
Key Responsibilities:
• Develop kernel-focused RL environments to challenge models effectively
• Identify and design environments that emphasize niche hardware utilization
• Structure scoring methods that prevent manipulation by models
• Innovate and support hardware-focused projects
• Scale tasks to maximize training efficiency
Requirements:
• Expertise in C / C++ / CUDA with ...