Back
Metro location and broad senior role skills increase competition, but niche LLM automation narrows candidate pool.
Role requires specialized QA automation and LLM/testing domain knowledge, limiting cross-industry transferability.
Explicit 8+ years requirement plus mandatory Playwright/TypeScript and LLM testing expertise creates strict filters.
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Design, build, and maintain end-to-end automated test suites for a complex enterprise-grade Agent Development Platform covering Frontend, Backend, multi-tenant isolation, and long-running Temporal workflows.
Create adversarial and non-deterministic test strategies for LLM-driven behaviors, failure injection, performance, and reliability to ensure contractual guarantees hold release after release.
Integrate test automation into CI/CD pipelines as hard release gates and produce auditable, reproducible evidence for client milestone sign-offs with focus on scalability and maintaining quality at pace of delivery.
8+ years of test automation experience, including API testing and building test frameworks for others to adopt.
Strong proficiency in Playwright and TypeScript for automated test suite development.
Hands-on experience testing non-deterministic LLM-powered systems with statistical assertions and semantic scoring, plus experience in failure injection and testing asynchronous, event-driven systems (Temporal or similar workflow engines a strong plus).
Work Location: Chennai, India (Hybrid).
Experienced in quality engineering for complex, distributed platforms requiring statistical and adversarial testing techniques for AI/LLM-driven systems.
Skilled at integrating automated testing deeply into CI/CD pipelines with focus on reproducibility, trustworthiness, and client defensibility of test evidence.
Able to collaborate closely with AI engineers, platform engineers, and evaluation teams embedding quality from design onward, and mentor mid-level QA engineers.