Über diese Senior QA Engineer Stelle bei Keyloop
The Role:
As a Senior QA Engineer, you'll own quality across our product portfolio. You'll define and lead our quality strategy across the full platform, from backend services and agent orchestration through to omnichannel communications.
You'll work closely with engineers and product to build in quality from the start, not just a manual check at the end. You’ll design and execute tests to measure the quality of our AI agents, testing for probabilistic outputs, expected reasoning behaviours, performance and overall security.
What You'll Be Doing:
● Design and own the quality strategy for our AI agent platform, including approaches to testing non-deterministic, LLM-powered systems.
● Build and maintain automated test suites covering unit, integration, API, and end-to-end scenarios across our TypeScript/Node.js/React/Python stack.
● Develop evaluation frameworks for agent behaviour, testing reasoning quality, tool use, memory, and multi-step interaction flows.
● Test and validate our omnichannel communication platform across channels: web, messaging, voice, and beyond.
● Collaborate closely with engineers and define acceptance criteria that catch issues early in the development cycle.
● Champion a culture of quality across the team, reviewing test coverage in PRs, advocating for testability in system design, and raising the bar for what "done" means.
● Use and help shape AI-assisted testing tooling to accelerate coverage and surface issues faster.
What We're Looking For:
● Proven experience as a Senior QA Engineer on complex, production software products.
● Strong hands-on skills using test frameworks (e.g. Playwright, Cypress, Jest).
● Experience testing APIs, backend services, and databases (PostgreSQL or similar).
● A clear understanding of how to approach testing non-deterministic systems.
● Experience designing and implementing QA strategy.
● Strong communication skills, you can articulate quality risks clearly to both engineers and non-technical stakeholders
Nice to have:
● Experience evaluating LLM or agentic systems, prompt behaviour, output quality, hallucination risks, or agent evaluation frameworks.
● Familiarity with performance, load, or chaos testing for real-time or event-driven systems.
● Background in automotive, dealership tech, or B2B SaaS.
● Exposure to AI-assisted development and testing tools (e.g. GitHub Copilot, Cursor, Claude Code).
