AI Augmented QA Engineer

Straker Ltd; Upper Harbour; Hybrid; NZD 90,000 - 140,000; Full time

Job summary

Straker Ltd in Auckland invites an AI-Augmented QA Engineer to build and own quality infrastructure across pods. You will design AI-driven test frameworks and ensure safe deployment of AI features.

The role blends automated testing, exploratory checks, and performance validation, with a focus on preventing AI-related failures while accelerating delivery. This is a hybrid, fixed-term role from ASAP to 28 May 2027.

Qualifications

• Understanding of test strategy, design, coverage and risk.
• Experience building automation in Python and Playwright.
• Familiarity with AI-assisted testing and prompt engineering.

Responsibilities

• Design AI-powered testing frameworks used by multiple pods.
• Use AI tools to transform feature specs into test plans and edge-case tests.
• Perform manual and exploratory testing when automation is unavailable.
• Build load-testing infrastructure for high-throughput scenarios.
• Identify AI-generated code risks and add automated checks.
• Create a shared library of test assets for reuse.

Skills

AI testing mindset

Python proficiency

Exploratory testing

Prompt engineering

Self-directed

Education

Bachelor's in CS or related field

Tools

Playwright

Selenium

CI/CD pipelines

Git

Job description

AI Augmented QA Engineer

Location: Auckland, Hybrid Department: Engineering | Role Type: Shared Service / Force Multiplier Fixed Term Role - ASAP to 28th May 2027

THE MISSION

The AI-Augmented QA Engineer builds and owns our quality infastructure. Unlike traditional QA roles, you don't sit inside a single pod to manually click through features; you serve as a force multiplier across all pods. Your mission is to build the automated frameworks and AI-orchestrated tooling that allow Product Engineers to verify their own work with confidence.

This is a "Quality-as-Code" role. In an environment moving at AI-augmented speeds, you are responsible for building the safety nets that catch characteristic AI failures- hallucinated logic, shallow error handling, and compliance gaps- before they ever reach production. You don't gatekeep delivery; you accelerate it by making high-quality shipping the path of least resistance.

WHAT YOU WILL DO

• Infrastructure Design: Build and maintain AI-orchestrated frameworks (Python/Playwright) that are modular and usable by every pod.
• AI-Generated Strategy: Use AI tools (Cursor, Claude, and others)to transform feature specs into comprehensive test plans, specifically hunting for obscure edge cases and failure scenarios.
• Hands-On Testing: Perform manual and exploratory testing where automated coverage doesn't yet exist. Know where the risks are in the product surface and prioritise accordingly.
• Stress & Scale: Build load-testing infrastructure to simulate high-throughput scenarios across our translation APIs and verification pipelines.
• AI Code Verification: Identify where AI-generated code introduces security gaps or hallucinated compliance behaviour, and build automated detection into the shared quality layer.
• Shared Asset Library: Develop a central repository of test assets that pods can extend and reuse, preventing "reinventing the wheel" across the organization.

WHAT WE ARE LOOKING FOR

AI-Augmented Testing

• AI as a daily tool: You already use AI in your workflow - coding assistants, test generation, prompt engineering. Not curious about AI; already doing it.
• The Irony of AI: You understand that AI can generate tests that pass without actually covering failure modes. You have the intuition to catch these "false positives".
• Automated Generation: Experience using AI to generate test plans, edge case scenarios, and automation scripts, coupled with the technical depth to verify their validity.

Technical Foundation

• Testing Fundamentals: You understand test strategy, test design, coverage and risk - not just how to write a test script.
• Python Proficiency: You can write and maintain test automation, scripts and frameworks in Python.
• Tooling: Experience with test automation frameworks (Playwright, Selenium, or similar) and CI/CD pipeline integration.
• Failure Pattern Recognition: Knowledge of where AI-generated code commonly stumbles: security boundaries, data validation, and overconfident logic.

Mindset

• Self Directed: You figure things out, ask good questions, and don't wait for someone to hand you a process
• Cross-Team Fluency: This role is shared across engineering pods with different contexts and cadences. You manage that without being managed.
• Prevention over Detection: You don't just find bugs; you design systems that prevent them from being written in the first place.
• Speed + Rigor: You are comfortable working at the intersection of velocity and discipline, understanding that in 2026, you cannot have one without the other.

Nice-to-Haves

• Familiarity with load testing and performance testing tools
• Exposure to compliance and security testing patterns (GDPR, data handling)
• Additional languages beyond Python (TypeScript, JavaScript)
• Background in localisation, language technology, or NLP-adjacent domains
• Experience in smaller, fast-moving companies where you wear multiple hats

WHY THIS ROLE?

You won't be stuck in a repetitive manual testing loop. You’ll be building the AI-driven quality engine of a modern tech company. You’ll have a bird's-eye view of the entire technical landscape, influencing the standards of every pod at Straker

If you're the kind of person who sees AI as a tool to be wielded rather than a threat to be managed - this is the role for you!