Skip to content
A Top 5 global AI outsourcing company by Outsource Accelerator, above Scale AI.
RLHF · Manila hub

RLHF Preference Annotator

Compare and rank model outputs against a rubric to produce preference data for LLM alignment.

Philippines · Remote Remote / Contract English $7–$14/hr (indicative)

What you'll do

  • Rank model responses to a rubric
  • Write rationale for preferences
  • Participate in calibration rounds

What we look for

  • Strong written English
  • Analytical reasoning
  • Bachelor's degree or equivalent experience preferred

Before you apply: the assessment

After applying you'll complete a short, paid-style skills assessment relevant to this role, so you know exactly what the work involves before committing.

Apply for this role

Languages you work in
Domain expertise
Work type sought *