ABOUT THIS FEATURED OPPORTUNITY
The QA Engineer will join the Channel Sales and Operations team to help ensure the reliability and quality of our AI/ML-powered B2B chatbot and the foundational platforms supporting it. This role goes beyond testing outputs you'll be working closely with engineers to ensure the end-to-end system, including cloud infrastructure and data pipelines, functions as intended.
THE OPPORTUNITY FOR YOU
Design and execute manual and automated test cases for GenAI platforms and chatbot systems.
Build and maintain Python-based test automation frameworks for backend services and ML pipeline validation.
Utilize RAGAS or similar tools to assess LLM outputs for factuality, relevance, and system performance.
Conduct end-to-end testing from data ingestion to user-facing output.
Validate system stability across GCP cloud components compute, storage, networking, and containers.
Identify failures not only in chatbot answers, but also in underlying infrastructure and platform behavior.
Collaborate with DevOps and ML engineers to triage bugs and optimize performance.
Ensure test coverage spans across multiple deployment environments including Kubernetes clusters and cloud VMs.
Requirements
KEY SUCCESS FACTORS
3+ years of QA Automation Engineering experience
-
Experience with Playwright for automated application testing, including sign-in and SSO authentication flows
-
Ability to design tests that validate output accuracy and system behavior across different user flows
-
Experience with Python API testing using requests, Pytest, and integration into CI/CD and cloud environments
Proficiency in writing and debugging Bash scripts used in CI/CD and cloud deployment workflows
Experience with Cloud platforms ( GCP preferred), including Kubernetes (kubectl experience is a plus), virtual machines, databases, cloud networking and storage components
- Understanding of modern cloud architecture and how distributed components interconnect in production environments
NICE TO HAVES
Experience with LLM testing frameworks like RAGAS , and ability to interpret metrics such as factuality, relevance, and performance
Experience with monitoring and observability tools
Familiarity with the end-to-end architecture of GenAI solutions , including vector stores, retrievers, embedding models, and inference systems