Business Operations Expert - Evaluator

Mercor; Sydney; Remote; AUD 96,000 - 138,000; Full time

Job summary

Mercor is seeking a Business Domain Expert to pilot AI model evaluation tasks on a contract basis. The role involves judging model outputs, writing evidence-grounded rationales, and providing structured feedback within tight deadlines. Remote work is available, with compensation per hour.

Ideal candidates have 5+ years in Admin, Marketing, HR, or Accounting and can work independently under time pressure. This position values practical judgment and clear documentation.

Qualifications

• 5+ years of hands-on professional experience in Admin, Marketing, Human Resources, or Accounting.
• Currently or recently practicing to judge work as a working professional would.
• Ability to write clear, specific, evidence-grounded rationales for judgments.
• Reliable within a short turnaround window.

Responsibilities

• Solve one realistic, domain-specific task using the provided source files.
• Review five model-generated outputs for the task. Rank them 1–5 with no ties, score each 0–100, and write evidence-based rationales citing specific parts of the output.
• Provide structured feedback on the task and study design.
• Work independently to meet deadlines within a short turnaround window.
• Use professional judgment as no rubric or golden answer is provided. LLMs or AI assistants are prohibited at every stage.

Skills

Admin experience

Marketing experience

HR experience

Accounting experience

Job description

About the job

Mercor connects elite creative and technical talent with leading AI research labs. Headquartered in San Francisco, our investors include Benchmark, General Catalyst, Peter Thiel, Adam D'Angelo, Larry Summers, and Jack Dorsey.

Position: Business Domain Expert — AI Model Evaluation Pilot (Admin, Marketing, HR, Accounting)
Type: Contract
Compensation: $70–$100/hour
Location: Remote

Role Responsibilities

• Solve one realistic, domain-specific task using the provided source files.
• Review five model-generated outputs for the task. Rank them 1–5 with no ties, score each 0–100, and write evidence-based rationales citing specific parts of the output.
• Provide structured feedback on the task and study design.
• Work independently to meet deadlines within a short turnaround window.
• Use professional judgment as no rubric or golden answer is provided. LLMs or AI assistants are prohibited at every stage.

Qualifications

Must-Have

• 5+ years of hands‑on professional experience in Admin, Marketing, Human Resources, or Accounting.
• Currently or recently practicing to judge work as a working professional would.
• Ability to write clear, specific, evidence‑grounded rationales for judgments.
• Reliable within a short turnaround window.