AI Agent Evaluator - Real-Life Assistant Tester

Dover; Northern (KY); Remote; USD 3,444,000 - 4,822,000; Part time

Benefits offered by this job

Remote work

Job summary

Dover is seeking an AI Agent Evaluator contractor based in the United States to test two AI agents by performing real-life tasks and recording outcomes. You will assess usability, accuracy, and user experience, providing detailed feedback from your own accounts on your phone.

You’ll use your bachelor’s degree and 2–3 years of relevant experience to document steps, note any issues, and rate performance. This role is remote and offers flexible scheduling.

Qualifications

• US-based with a Bachelor's degree.
• 2-3 years of experience in engineering, business management, or office/operations.
• Detail-oriented and able to document each step clearly.

Responsibilities

• Run real-life scenarios with two AI agents and score outcomes.
• Approve or stop the agent at key steps during tasks.
• Screen record every attempt and observe usability and accuracy.
• Provide clear written feedback on agent experience and performance.
• Score results on completion, quality, control issues, satisfaction and time.

Skills

ChatGPT

Muse

AI agents

Attention to Detail

Following Instructions

Screen Recording

Education

Bachelor's degree

Job description

Dover is seeking an AI Agent Evaluator contractor based in the United States to test two AI agents by performing real-life tasks and recording outcomes. You will assess usability, accuracy, and user experience, providing detailed feedback from your own accounts on your phone.

You’ll use your bachelor’s degree and 2–3 years of relevant experience to document steps, note any issues, and rate performance. This role is remote and offers flexible scheduling.