Remote AI Evaluation — Bilingual Russian Psychologist (PhD)

AuraOne; United States; Remote; USD 34,000 - 55,000; Part time

Job summary

AuraOne is seeking a remote AI evaluation contractor to review Russian generalist model outputs. You will apply a versioned rubric, provide rationales, and assign severity tags for quality control.

Responsibilities include comparing responses, labeling issues, and calibrating against gold-standard examples weekly. Strong attention to detail and async availability of at least 10 hours/week are required.

Qualifications

• Prior evaluation, annotation, or human-rater experience on russian generalist evaluation or adjacent content for Bilingual Russian Psychologist (PhD) — Remote AI Evaluation work.
• Comfort applying multi-page rubrics consistently across long batches.
• Clear written reasoning that names the issue and the rubric clause being applied.
• Strong attention to detail and the ability to flag when a prompt itself is the problem.
• Reliable async availability for at least 10 hours per week.

Responsibilities

• Evaluate russian generalist evaluation model outputs against a versioned rubric and assign severity tags for Bilingual Russian Psychologist (PhD) — Remote AI Evaluation assignments.
• Compare paired responses and pick the stronger answer with a written rationale.
• Label hallucinations, instruction-following failures, and unsafe content with structured tags.
• Capture ambiguous prompts and route them back to the program team for rubric updates.
• Maintain reviewer-quality scores by calibrating against gold-standard examples each week.
• Document recurring failure modes so the modeling team can target them in the next training run.

Skills

Model output evaluation

Rubric-based annotation

Severity tagging

Inter-rater calibration

Russian generalist evaluation

Education

PhD in Psychology

Job description

AuraOne is seeking a remote AI evaluation contractor to review Russian generalist model outputs. You will apply a versioned rubric, provide rationales, and assign severity tags for quality control.

Responsibilities include comparing responses, labeling issues, and calibrating against gold-standard examples weekly. Strong attention to detail and async availability of at least 10 hours/week are required.