Remote: AI Agent Evaluation Scenario Designer

Mindrift; Kentucky; Remote; USD 68,191 - 97,120; Part time

Benefits offered by this job

Flexible schedule

Competitive hourly pay up to $60

Remote work opportunity

Experience with advanced AI projects

Job summary

A forward-thinking technology company is looking for a detail-oriented individual to design structured evaluation scenarios for AI agents. This entry-level part-time role allows you to contribute remotely, creating test cases for LLM-based agents. The ideal candidate will have a background in Computer Science and some experience with software testing. Flexibility is key as you engage with innovative AI projects while working at your own pace.

Qualifications

• Degree in Computer Science, Software Engineering, Data Science, AI, or similar.
• Background in QA, software testing, data analysis, or annotation.
• Ability to switch between tasks quickly and work with complex guidelines.

Responsibilities

• Design structured test scenarios based on real-world tasks.
• Define acceptable agent behavior and scoring logic.
• Review agent outputs and adapt tests accordingly.

Skills

Analytical mindset

Attention to detail

Good understanding of test design principles

Strong written communication skills

Basic experience with Python

Basic experience with JavaScript

Curiosity about AI-generated content

Education

Bachelor's or Master's Degree in Computer Science or related fields

Tools

JSON

YAML

Job description

A forward-thinking technology company is looking for a detail-oriented individual to design structured evaluation scenarios for AI agents. This entry-level part-time role allows you to contribute remotely, creating test cases for LLM-based agents. The ideal candidate will have a background in Computer Science and some experience with software testing. Flexibility is key as you engage with innovative AI projects while working at your own pace.