Back
Remote role with metro hubs but niche LLM QA specialization yields moderate applicant competition.
High because specialized LLM, Temporal workflow, and adversarial QA expertise is niche and less transferable across industries.
High due to explicit 8+ years, mandatory Playwright/TypeScript, and specialized LLM and reliability experience.
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Own and build comprehensive automation test suites covering Frontend, Backend, and long-running workflows to ensure platform reliability and multi-tenant isolation.
Develop adversarial and non-deterministic test strategies for AI-driven behaviors including failure injection and statistical assertions to verify system resilience and compliance with client contractual commitments.
Integrate automated suites as hard release gates within CI/CD pipelines, produce reproducible test evidence for client milestone approvals, and mentor mid-level QA engineers in AI testing frameworks.
8+ years of experience in test automation with API testing and building test frameworks used by engineering teams.
Strong proficiency in Playwright and TypeScript for developing automated test suites is mandatory.
Hands-on experience testing LLM-powered or other non-deterministic systems with statistical assertions and managing model variance.
Experience with asynchronous, event-driven systems and failure injection techniques; familiarity with Temporal or similar workflow engines is a strong plus.
Experienced in building and maintaining high-security CI/CD integrated test automation frameworks with a focus on reliability and measurable quality evidence.
Demonstrates domain expertise in AI/LLM behaviors, adversarial/security testing, statistical analysis for evaluation, and complex multi-tenant SaaS environments.
Skilled at collaborating with AI engineers and evaluation teams early in the design stage to embed testability, quality, and observability into platform architecture.