RLHF Evaluation Specialist for AI Training

Rex.zone; Canada; Remote; CAD 56,714 - 94,524; Part time

Job summary

A tech company specializing in AI is seeking an AI Trainer based in Canada. The role involves improving large language models through RLHF-style evaluations, prompt evaluation, and data labeling. Candidates should have experience with structured evaluation, strong writing skills, and familiarity with AI evaluation workflows. This position offers an hourly pay range of $30 to $50. Apply by highlighting your relevant experience and compliance with annotation guidelines.

Qualifications

• Experience with structured evaluation and guideline-driven judgment.
• Strong writing skills for documenting rationales and edge-case notes.
• Comfort with data labeling and QA evaluation processes.

Responsibilities

• Perform RLHF evaluations and write clear rationales.
• Execute prompt evaluations focusing on instruction-following and safety.
• Document edge cases and build error taxonomies.

Skills

Structured evaluation

Strong writing

Familiarity with RLHF and LLM evaluation

Data labeling

Multilingual evaluation

Job description

A tech company specializing in AI is seeking an AI Trainer based in Canada. The role involves improving large language models through RLHF-style evaluations, prompt evaluation, and data labeling. Candidates should have experience with structured evaluation, strong writing skills, and familiarity with AI evaluation workflows. This position offers an hourly pay range of $30 to $50. Apply by highlighting your relevant experience and compliance with annotation guidelines.