QA Engineer – AI Agents & Automation

Job Description

Role Summary

You’ll own quality across a multi-agent AI platform where systems reason, collaborate, and execute workflows autonomously. This is not traditional QA — you’ll be testing behaviour, decision-making, and system reliability under real-world complexity.

Key Responsibilities

• Define and drive test strategy for agent-based and distributed systems
• Validate agent reasoning, orchestration logic, and tool interactions
• Build and scale automation across API, UI, and asynchronous workflows
• Ensure system reliability (failures, retries, state consistency, idempotency)
• Identify edge cases in AI outputs and multi-agent interactions
• Collaborate closely with engineering on acceptance criteria and quality standards

Core Requirements

• Strong QA automation experience (API, UI, integration)
• Experience with microservices, event-driven or async systems
• Hands-on with tools like Playwright, Cypress, Selenium, and Postman
• Ability to design test strategies, not just execute tests
• Analytical mindset with focus on edge cases and system behaviour

Preferred Experience

• Testing AI/LLM systems or agent workflows
• Familiarity with orchestration frameworks (e.g. Temporal-style systems)
• Experience with stateful or dynamic workflows

Mindset

• Thinks like a user, tests like an attacker
• Proactive, ownership-driven, and comfortable with ambiguity
• Genuinely interested in AI-native, cloud-native systems