Expert QA Tester for AI Automation Platform

Job ID: 39997919

Budget: £10 – £15 GBP

QA Tester to test AI-Powered Test Automation Platform

Overview
We are looking for an experienced QA Tester to help evaluate a next-generation, AI-driven test automation platform. The platform converts written requirements into test scenarios, generates Playwright automation, executes tests autonomously, self-heals failures, and produces reports and defect outputs without human scripting.

Your role will be to thoroughly test the platform itself—its workflow, reliability, accuracy, and ease of use—by acting as a hands-on evaluator and providing structured feedback.

Key Responsibilities
1. Functional Testing of the AI Workflow

You will test the full end-to-end workflow, including:

Uploading or entering requirements

Generating test scenarios

Reviewing scenario accuracy

Triggering autonomous test automation generation

Running the execution suite

Reviewing results, logs, videos, and defect outputs

Exporting to CI/CD

2. Accuracy & Reliability Checks

Validate scenario coverage against the provided requirements

Assess the quality of the generated test automation (Playwright)

Spot false positives/false negatives in execution results

Confirm the self-healing engine behaves as expected

3. Usability & UX Feedback

Identify confusing steps, unclear UI patterns, or friction points

Suggest improvements to simplify or streamline the workflow

4. Edge Case & Negative Testing

Explore unusual input formats

Test incomplete or ambiguous requirements

Break the workflow intentionally to discover failure modes

5. Reporting

Produce concise reports of findings

Document any bugs, gaps, or inconsistencies

Provide improvement recommendations

Required Skills

Strong background in software testing (manual or automation)

Experience with Playwright, Cypress, or similar automation frameworks

Ability to evaluate AI-generated test cases & automation code

Familiarity with modern QA workflows (requirements → scenarios → automation)

Detail-oriented mindset and clear communication skills

Nice to Have

Experience with LLM/AI tools in testing

Understanding of RAG, self-healing automation, or AI agents

Familiarity with CI/CD pipelines

Engagement Details

Short-term freelance contract

Remote

Expected workload: 10–20 hours per week for 2–4 weeks

Flexible hours

Clear deliverables at the end of each week