Quality Assurance Engineer

NodeShift is looking for a QA Engineer who writes automation first and uses AI to move faster. You will own the quality of your features end to end, from reviewing requirements to automated tests running in CI. You will also help test AI agents and LLM pipelines, which is a different game from classic web QA. Working with AI is a hard requirement for this role - AI is your default way of testing, used every day to design, write, run, and debug tests.
Key Responsibilities
Write and maintain end-to-end, UI, and API tests in Playwright + TypeScript, following the team's framework conventions.
Run tests in CI (GitHub Actions), keep suites fast and stable, and fix flaky tests instead of retrying them.
Prepare test data and environments, and mock external services where needed.
Help build and run evaluation datasets for LLM and agent features, checking accuracy, hallucinations, and regressions after prompt or model changes.
Use traces in Langfuse to reproduce and pin down issues in agentic pipelines.
Test LLM-specific risks: prompt injection, unsafe outputs, and PII leakage.
Review requirements and designs early, and write test plans and acceptance criteria together with developers.
Run exploratory and regression testing where automation doesn't pay off.
Report bugs developers can act on straight away: clear steps, logs, evidence, and severity.
Generate test cases, edge cases, and test data from requirements and Jira tickets with AI.
Write, refactor, and fix automated tests with AI coding agents (Claude Code, Codex, Cursor, Playwright MCP, or similar).
Run exploratory testing with AI browser agents, and use AI to analyze test failures, logs, and traces.
Suggest and try out AI tools that make the team's QA faster.
Skills & Requirements
API Testing
Arabic
CI/CD
Docker
Git
Kubernetes
LLM Testing
Performance Testing
Playwright
Python
Security Testing
TypeScript
Additional Information
Work Experience
3+ years of experience in QA
2+ years of experience writing automated tests
Experience with B2B, enterprise, or government/regulated products
Project Details
You will work on AI agents and LLM infrastructure used by enterprise and government clients in the GCC. You will test agentic AI pipelines, document processing, and LLM gateways running on Kubernetes in regulated environments where quality, security, and data residency are critical.

Work arrangement
Yes