Location
toronto, on, Canada
Posted
June 27, 2026
Job Description
Shape the future of AI security as a Security Research Engineer at Preference Model. Develop reinforcement learning environments that empower LLMs to tackle real-world cybersecurity problems.
In this pivotal role, you'll design high-quality environments that emulate various security tasks using multiple programming languages. Join a dedicated team of experts aiming to push AI closer to its potential while addressing critical vulnerabilities and exploiting solutions. Collaborate to refine and innovate environment processes effectively.
Key Responsibilities:
• Create RL environments that represent real-world vulnerabilities
• Develop tasks for discovering, exploiting, and patching vulnerabilities
• Validate security signals using industry-standard tools
• Collaborate with other experts in the field for process improvements
• Ensure high standards in handling security-focused modeling
Requirements:
• In-depth understanding of cybersecurity threats and solutions<...
In this pivotal role, you'll design high-quality environments that emulate various security tasks using multiple programming languages. Join a dedicated team of experts aiming to push AI closer to its potential while addressing critical vulnerabilities and exploiting solutions. Collaborate to refine and innovate environment processes effectively.
Key Responsibilities:
• Create RL environments that represent real-world vulnerabilities
• Develop tasks for discovering, exploiting, and patching vulnerabilities
• Validate security signals using industry-standard tools
• Collaborate with other experts in the field for process improvements
• Ensure high standards in handling security-focused modeling
Requirements:
• In-depth understanding of cybersecurity threats and solutions<...