Back
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Remote role but highly specialized LLM-testing skills and senior requirement reduce broad applicant pool.
Core automation skills transferable, but LLM/Temporal/multi-tenant testing creates moderate domain specificity.
Explicit 8+ years, mandatory Playwright/TypeScript and LLM testing mandates make filters strict.
Own and design automated test suites for a complex Agent Development Platform, covering Frontend, Backend, workflows, multi-tenant isolation, and sandbox security.
Develop and maintain adversarial, AI-specific, statistical test strategies including failure injections and negative testing to ensure system reliability and compliance with NFRs.
Integrate test automation into CI/CD pipelines as hard release gates and collaborate closely with AI and platform engineers to embed quality from design to client milestone sign-offs.
8+ years of test automation experience, including API testing and building reusable test frameworks.
Strong proficiency with Playwright and TypeScript for building automation suites.
Hands-on experience testing LLM-powered or non-deterministic systems with statistical assertion and model variance management.
Experience with asynchronous, event-driven systems testing and CI/CD integration (e.g., GitHub Actions).
Experienced in building scalable automated test infrastructure for AI/LLM-driven platforms with deep understanding of non-deterministic testing challenges.
Comfortable contributing test infrastructure and synthetic data pipelines integrated into evaluation and CI processes for measurable quality.
Skilled in adversarial security testing and performance/reliability verification in complex multi-tenant SaaS or agentic systems.