Remote AI Evaluation Specialist & Rubric Designer

Crossing Hurdles; Philippines; On-site; PHP 334,800 - 468,720; Full time

Job summary

Crossing Hurdles is seeking a meticulous evaluator to design and implement concrete AI evaluation tasks with clear prompts, rubrics, and supporting materials. You will observe AI behavior, craft precise English reports, and collaborate with teams to refine benchmarking methods.

The role emphasizes strong writing, attention to detail, and structured assessment practices. You will contribute to robust evaluation frameworks, document findings succinctly, and help drive continuous improvement in AI

Qualifications

• Have experience in roles emphasizing written precision and structured thinking (paralegal, executive assistant, junior analyst, librarian, QA analyst).
• Native or fluent English writing; able to produce concise, specific, unambiguous observations.
• Proven skill designing or applying rubric-based evaluation and scoring frameworks.

Responsibilities

• Design and implement self-contained evaluation tasks, including prompts, supporting files, and detailed grading rubrics.
• Meticulously observe AI agent behaviors and produce precise summaries and reports in high-quality English.
• Iterate and refine evaluation tasks and rubrics based on feedback and teamwork to ensure robust benchmarking.
• Collaborate with the customer’s team to share insights and drive continuous improvement in evaluation techniques.

Skills

Written precision

Structured thinking

Rubric design

Attention to detail

Clear communication

Job description

Crossing Hurdles is seeking a meticulous evaluator to design and implement concrete AI evaluation tasks with clear prompts, rubrics, and supporting materials. You will observe AI behavior, craft precise English reports, and collaborate with teams to refine benchmarking methods.

The role emphasizes strong writing, attention to detail, and structured assessment practices. You will contribute to robust evaluation frameworks, document findings succinctly, and help drive continuous improvement in AI