RLHF Strategist Expert (AI Community)

About the Role:

At TELUS Digital, we use Reinforcement Learning from Human Feedback (RLHF) to align AI with human values, and in this role, you act as our "Logical Compass." We believe that AI should be helpful, honest, and harmless; you are the one who designs the strategies and rubrics to make that a reality. You will teach AI how to reason and how to maintain a consistent, helpful persona across different cultural contexts. At TELUS, you aren't just ranking data; you are defining the ethics of tomorrow’s AI.

Key Responsibilities:

• Conceptualize and draft multi-dimensional grading rubrics that evaluate AI responses for tone, logic, and instructional following.
• Lead quality-assurance audits for large-scale annotation projects, ensuring the human-feedback loop is optimized for model learning.
• Investigate complex "hallucinations" and logical fallacies in model outputs, developing prompt-engineering strategies to mitigate them.
• Interface with project stakeholders to define the "Ideal Response Profile" for specific industries or user personas.