Freelance AI Evaluation & QA Engineer (Remote)

Mindrift; Calabarzon; Remote; PHP 1,722,000 - 2,583,000; Part time

Job summary

Mindrift connects specialists with project-based AI opportunities for leading tech companies. You’ll build realistic developer environments and design tasks for evaluating AI coding agents. This is a remote, part-time freelance role focused on testing, evaluation, and policy creation.

You will craft prompts, write tests, and ensure solutions are robust across multiple valid approaches, working with a global team and flexible schedules.

Qualifications

• 5+ years in software development and testing.
• Experience with QA-automation or cybersecurity roles is preferred.
• Proficiency in English at least B2.

Responsibilities

• Create tasks and evaluation criteria for AI coding agents.
• Design tests that accept multiple valid solutions.
• Evaluate agent outputs and iterate requirements.

Skills

Python

JavaScript/TypeScript

Docker

PostgreSQL

Kafka

Redis

React

QA/Automation

Testing

English Proficiency

Education

Master's Degree in CS/SE/AI/Data Science

Bachelor's with 5 years experience

Tools

FastAPI

Git

Job description

Mindrift connects specialists with project-based AI opportunities for leading tech companies. You’ll build realistic developer environments and design tasks for evaluating AI coding agents. This is a remote, part-time freelance role focused on testing, evaluation, and policy creation.

You will craft prompts, write tests, and ensure solutions are robust across multiple valid approaches, working with a global team and flexible schedules.