Remote RLHF Strategist for AI Ethics & Evaluation

TELUS Digital; Argentina; Remote; ARS 41,729,000 - 104,323,000; Full time

Benefits offered by this job

Remote work

Independent contractor

Global collaboration

Job summary

TELUS Digital seeks a Logical Compass to design RLHF grading rubrics ensuring AI responses are helpful, honest, and harmless. You will craft multi-dimensional rubrics, lead QA audits for large annotation projects, and address hallucinations with targeted prompt-engineering strategies.

As an independent contractor, you will collaborate with a global community of experts, assess AI outputs across industries, and shape ethical standards and evaluation criteria for responsible AI deployment.

Qualifications

• Education: Bachelor’s Degree (CS, AI, Data Science or Humanities).
• English proficiency of at least B1 (Intermediate).
• Native-level fluency in at least one language.

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, optimizing the human-feedback loop.
• Investigate 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.

Skills

Exceptional writing

Logic-based decision making

English proficiency (B1)

Education

Bachelor’s Degree

Job description

TELUS Digital seeks a Logical Compass to design RLHF grading rubrics ensuring AI responses are helpful, honest, and harmless. You will craft multi-dimensional rubrics, lead QA audits for large annotation projects, and address hallucinations with targeted prompt-engineering strategies.

As an independent contractor, you will collaborate with a global community of experts, assess AI outputs across industries, and shape ethical standards and evaluation criteria for responsible AI deployment.