Quality Guardian (QA Lead)

The Opportunity

We're working with a fast-moving organization looking for a Quality Guardian — a QA lead responsible for making sure zero critical or high-severity bugs ever reach production. This role goes well beyond traditional testing: alongside owning test strategy, automation, and defect management, you'll also be responsible for validating AI and LLM-powered products before they reach clients including RAG quality, safety red-teaming, and non-deterministic output evaluation. If you want to own quality end-to-end from a Cypress test suite to an LLM-as-judge evaluation pipeline this role gives you both.

What You'll Do

• Own testing strategy: design test plans covering happy paths, edge cases, integration, performance, and security
• Build automated test suites (unit, integration, E2E) that run in CI/CD for fast, confident releases
• Execute manual, exploratory, usability, and regression testing across the full stack
• Run performance and load testing (k6/JMeter/Locust) and security testing (OWASP Top 10, Burp Suite, dependency scanning)
• Manage defects end-to-end: systematic logging, severity triage, root-cause analysis, and process improvement
• Validate AI products pre-release: golden datasets, LLM-as-judge scoring, human review for high-risk cases, and drift/instability testing
• RAG testing: retrieval quality, source relevance, answer faithfulness, citation accuracy, and fallback handling
• AI safety & red-teaming: adversarial testing for prompt injection, jailbreaks, harmful content, data leakage, and biased outputs
• Own client-release gates — blocking release when AI risk, evaluation scores, or safety thresholds aren't met
• Track and report quality metrics: coverage, defect escape rate, pass rate, and trend reporting to delivery leadership