Instruction Tuning Preference Data Reviewer

AuraOne, Inc.; United States; Remote; USD 34,000 - 62,000; Full time

Job summary

AuraOne, Inc. is seeking an Instruction Tuning Preference Data Reviewer to remotely evaluate model outputs against a versioned rubric and assign severity tags. You will compare paired responses, label edge cases, and provide structured feedback for retraining.

Ideal candidates have prior annotation experience, strong attention to detail, and can work asynchronously at least 10 hours per week from the U.S. This contractor role supports AuraOne’s data quality and safety review workflows.

Qualifications

• Prior evaluation, annotation, or human-rater experience on instruction tuning data evaluation.
• Ability to apply multi-page rubrics consistently across long batches.
• Able to provide clear written reasoning naming the issue and rubric clause.
• Strong attention to detail and ability to flag prompts that are the problem.
• Reliable async availability for at least 10 hours per week.

Responsibilities

• Evaluate instruction tuning preference data evaluation model outputs against a versioned rubric and assign severity tags.
• 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

Prior evaluation annotation or human-r

Rubric-based multi-page evaluation

Clear written reasoning naming issue &

Job description

Instruction Tuning Preference Data Reviewer is a remote evaluation track for reviewing instruction tuning preference data evaluation prompts and responses against AuraOne's quality rubric. Reviewers compare paired outputs, label edge cases, and write the kind of structured feedback the modeling team can use to retrain.

Why this role matters

AI data reviewers help turn instruction tuning preference data evaluation outputs into auditable labels, rationales, and regression cases for AuraOne Human Data.

Responsibilities

• Evaluate instruction tuning preference data evaluation model outputs against a versioned rubric and assign severity tags for Instruction Tuning Preference Data Reviewer 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.

Qualifications

• Prior evaluation, annotation, or human-rater experience on instruction tuning preference data evaluation or adjacent content for Instruction Tuning Preference Data Reviewer 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.

Example tasks

• Compare two instruction tuning preference data evaluation model responses to the same prompt and pick the stronger one with rationale.
• Tag an unsafe response with the correct policy category and severity.
• Audit a 50-row batch for rubric consistency and report drift to the program lead.
• Propose a rubric clarification after spotting a recurring failure mode.

Nice to have

• Background in linguistics, content moderation, or trust & safety review.
• Experience with inter-rater agreement metrics and calibration cycles.
• Domain expertise that lets you spot subject-matter errors automated checks miss.

Skills

• Model output evaluation
• Rubric-based annotation
• Severity tagging
• Inter-rater calibration
• Instruction Tuning Preference Data evaluation
• Preference ranking
• RLHF
• Rater calibration
• Instruction
• Tuning

Work model

Remote — US-eligible. Remote · Independent specialist contractor. Employment type: CONTRACTOR. Applicants must be authorized to work from US.

Compensation

Hourly rate confirmed after the interview process.

Application process

Apply through AuraOne's specialist intake for role-specific routing and review. Final project scope, schedule, and contractor terms are confirmed before placement.