_{15th May, 2026}

Automation Test Engineer
Melbourne CBD (Hybrid)
$950 per day
12 Month Contract

The Opportunity

Our client is a household name undergoing one of the most significant digital transformations in their sector. Their engineering team is building and scaling AI-powered customer platforms at pace, and this role sits at the centre of ensuring those platforms are tested, reliable and continuously improving.

This isn't a standard test engineering role. The core product is a live AI assistant serving hundreds of thousands of customers across multiple channels, and the team is operating at the frontier of AI-assisted engineering, using agentic coding tools, MCP-connected workflows and LLM output validation as part of everyday delivery. If you have been waiting for a QA role that takes AI seriously, this is it.

What You'll Be Doing

Building and maintaining Playwright automation frameworks with MCP integration, enabling AI-driven browser automation and intelligent test generation at scale. Owning the validation of AI-generated outputs, assessing response quality, behavioural consistency and safety across ongoing model changes. Using coding agents like Claude Code and GitHub Copilot as everyday tools to write tests faster, improve code quality and keep the framework moving. Connecting tooling across Slack, Jira, Confluence and Postman to keep defect visibility and test reporting streamlined across the team. Running end-to-end, API and performance testing across new and existing platform features while working closely with developers, product owners and business analysts throughout delivery.

What We're Looking For

• Solid Playwright experience with working knowledge of MCP and how it applies to browser automation and AI-assisted workflows
• Strong TypeScript skills and a track record of building automation frameworks from the ground up
• Hands-on experience or genuine depth of interest in testing AI systems, understanding how to evaluate outputs that are probabilistic rather than deterministic
• Ability to design test strategies that account for variable AI outputs where the same input may not always produce the same result
• Comfortable using coding agents as part of daily engineering workflow rather than as an occasional productivity tool
• CI/CD experience and confidence working across pipeline tooling
• API testing depth using Postman or equivalent
• Working knowledge of Docker and cloud environments
• Someone who thrives in ambiguity, works autonomously and communicates clearly across technical and non-technical stakeholders

Helpful But Not Essential

• Experience connecting MCP integrations across workflow and project management tooling
• Background in prompt engineering or building evaluation frameworks for AI-generated content
• Performance testing experience
• Exposure to centralised logging or visual testing tooling
• Experience working within regulated industries or large-scale transformation programmes

Apply For Job