AuraOne logo

multi turn ranking preference data reviewer aoj frontier

Hiring from
United States
Work type
Remote
Posted

625,386 remote jobs, straight from company career pages

100% free · New jobs every minute

Show job description
All AI jobs

Human Data / RLHF & Human Preference Data

Multi-Turn Ranking Preference Data Reviewer

Multi-Turn Ranking Preference Data Reviewer is a remote evaluation track for reviewing multi turn ranking preference data evaluation prompts and responses against AuraOne's quality rubric.

ContractorRemote — US-eligibleHourly rate confirmed after the interview process.

About the role

Multi-Turn Ranking Preference Data Reviewer is a remote evaluation track for reviewing multi turn ranking 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.

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

Produce preference rankings, reward-model feedback, and calibrated human judgment for post-training pipelines.

Responsibilities

  • Evaluate multi turn ranking preference data evaluation model outputs against a versioned rubric and assign severity tags for Multi-Turn Ranking 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.

What you should bring

  • Prior evaluation, annotation, or human-rater experience on multi turn ranking preference data evaluation or adjacent content for Multi-Turn Ranking 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.

Role signals

Example tasks

  • Compare two multi turn ranking 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.

Useful experience

  • 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.

Compensation and schedule

Hourly rate confirmed after the interview process.

Expected arrangement: contractor, with program-defined task volume and review pacing. Placement depends on current program demand and reviewer confirmation.

Skills used in matching

  • Model output evaluation
  • Rubric-based annotation
  • Severity tagging
  • Inter-rater calibration
  • Multi Turn Ranking Preference Data evaluation
  • Preference ranking
  • RLHF
  • Rater calibration
  • Multi
  • Turn
  • Ranking

Application process

Submitting this form sends your application directly to the recruiting team for this specialist cohort.

About AuraOne

AuraOne is a human data company for AI teams and a workflow service for enterprises. It supplies expert judgment, speech, physical-world data and checked workflows.

More roles in RLHF & Human Preference Data

Review the full track
RLHF & Human Preference DataRecord 001

Ranking Rubric Reward Model Evaluator

Ranking Rubric Reward Model Evaluator is a remote evaluation track for reviewing ranking rubric reward model evaluation prompts and responses against...

ContractorRemote · Independent specialist contractorHourly rate confirmed after the interview process.
RLHF & Human Preference DataRecord 002

Reward Model Preference Data Reviewer

Reward Model Preference Data Reviewer is a remote evaluation track for reviewing reward model preference data evaluation prompts and responses against...

ContractorRemote · Independent specialist contractorHourly rate confirmed after the interview process.
RLHF & Human Preference DataRecord 003

Conversational Preference Reward Model Evaluator

Conversational Preference Reward Model Evaluator is a remote evaluation track for reviewing conversational preference reward model evaluation prompts...

ContractorRemote · Independent specialist contractorHourly rate confirmed after the interview process.
Apply for this job100% free