Full-time

Software Engineering Member - AI Environments

Posted by Preference Model • toronto, on, Canada

📍 toronto, on 🕒 June 27, 2026

About the Role

Join Preference Model to redefine software engineering challenges for AI models. This role centers on designing RL environments that reflect real-world complexities and enhance learning outcomes.
In this position, as a technical staff member, you will leverage your extensive software engineering skills to create high-quality training tasks. You will dive into system design problems and complex workflows, fostering the advancement of AI models by exposing their limitations.
Key Responsibilities:
• Design RL tasks through a full lifecycle
• Own challenging environments with realistic interactions
• Direct day-to-day coding agents' work
• Redesign tasks to target subtle model failures
• Contribute to the supporting infrastructure
Requirements:
• Proven deep software engineering expertise
• Skills in Python and agent coding
• Intuition for model behaviors without prior ML experience
• Independent problem-solving capabilities
• History of end-to-end pr...

Ready to Apply?

Submit your application today and take the next step in your career journey with Preference Model.

Apply Now