Search Generalists

Mercor is seeking detail-oriented Search Generalist Experts to support a high-impact project with a leading AI research lab. In this role, you will help evaluate and improve how advanced AI systems perform on real-world search and browsing tasks.

This work includes assessing model outputs for factuality, helpfulness, completeness, and judgment quality across a broad range of user queries. You will contribute to structured evaluation workflows that help train, benchmark, and refine frontier AI systems. This is a strong fit for excellent generalists who are sharp researchers, strong writers, and comfortable making nuanced quality judgments at scale.

Role Overview

Search Generalist Experts

factuality, helpfulness, completeness, and judgment quality

Key Responsibilities

Qualifications

Preferred Qualifications

Mercor is seeking detail-oriented Search Generalist Experts to support a high-impact project with a leading AI research lab. In this role, you will help evaluate and improve how advanced AI systems perform on real-world search and browsing tasks. This work includes assessing model outputs for factuality, helpfulness, completeness, and judgment quality across a broad range of user queries. You will contribute to structured evaluation workflows that help train, benchmark, and refine frontier AI systems. This is a strong fit for excellent generalists who are sharp researchers, strong writers, and comfortable making nuanced quality judgments at scale. Evaluate AI-generated search responses for factual accuracy, helpfulness, clarity, completeness, and overall quality. Assess whether models use search appropriately and whether search queries are well-formed and effective. Compare model responses side by side and provide concise, defensible rationales. Write and refine prompts, golden answers, rubric criteria, and edge cases for search-related evaluations. Apply project guidelines consistently across ambiguous, multi-step, and real-world search tasks. Identify recurring failure modes and escalate unclear cases or rubric gaps to project leads. Participate in calibration, QA, and feedback loops to maintain strong agreement and quality standards. Excellent written English and strong online research skills. Strong judgment when synthesizing information from multiple sources. Ability to distinguish factual accuracy from fluency, confidence, or style. High attention to detail and comfort following structured guidelines. Reliable, self-directed, and responsive in an asynchronous remote environment. Experience in search quality, fact-checking, content evaluation, trust and safety, annotation, QA, or prompt/rubric writing. Familiarity with search evaluation concepts such as factuality, helpfulness, severity, side-by-side comparisons, or tool-use assessment. Experience working with LLM evaluation workflows or human data projects. Multilingual skills are a plus. Bachelor’s degree preferred; advanced degree or strong professional background is a plus. We consider all qualified applicants without regard to legally protected characteristics and provide reasonable accommodations upon request.

• Evaluate AI-generated search responses for factual accuracy, helpfulness, clarity, completeness, and overall quality.
• Assess whether models use search appropriately and whether search queries are well-formed and effective.
• Compare model responses side by side and provide concise, defensible rationales.
• Write and refine prompts, golden answers, rubric criteria, and edge cases for search-related evaluations.
• Apply project guidelines consistently across ambiguous, multi-step, and real-world search tasks.
• Identify recurring failure modes and escalate unclear cases or rubric gaps to project leads.
• Participate in calibration, QA, and feedback loops to maintain strong agreement and quality standards.
• Excellent written English and strong online research skills.
• Strong judgment when synthesizing information from multiple sources.
• Ability to distinguish factual accuracy from fluency, confidence, or style.
• High attention to detail and comfort following structured guidelines.
• Reliable, self-directed, and responsive in an asynchronous remote environment.
• Experience in search quality, fact-checking, content evaluation, trust and safety, annotation, QA, or prompt/rubric writing.
• Familiarity with search evaluation concepts such as factuality, helpfulness, severity, side-by-side comparisons, or tool-use assessment.
• Experience working with LLM evaluation workflows or human data projects.
• Multilingual skills are a plus.
• Bachelor’s degree preferred; advanced degree or strong professional background is a plus.