Senior/Tech Lead QA with AI experience (Part-time)

N-iX is looking for a Senior/Tech Lead QA Engineer with AI experience to join our team.

We're looking for a hands-on Senior/Tech Lead QA Engineer who can cover the full testing spectrum: UI, API, and AI/ML output validation. You'll be joining a project building an AI-powered document analysis platform from the ground up. The system combines a CMS backend, modern UI, and a RAG-based AI layer used for intelligent document processing and analysis.

Key Responsibilities

• Follow a phased QA approach — begin with CMS and backend testing to establish a reliable baseline of expected system behavior, then apply those insights to validate AI agent outputs effectively
• Design and execute test cases for REST APIs, covering functional correctness, edge cases, error handling, authentication, and data integrity
• Perform UI testing across core user journeys, validating layout, behavior, and integration with backend services
• Transition into AI output validation once the deterministic layers are stable — using your knowledge of business rules to identify inconsistencies, hallucinations, or degraded outputs in agent responses
• Document and maintain test cases, test plans, and bug reports in a structured and traceable way
• Participate in requirement reviews and technical discussions to identify testability gaps early
• Collaborate with the Lead Big Data/AI Engineer and AI team to understand RAG pipeline behavior, document ingestion flows, and output quality expectations
• Contribute to building reusable test assets and QA processes as the project scales

Requirements

• 5+ years of experience in manual QA, with exposure to frontend, backend and AI testing
• Solid experience with API testing using tools such as Postman, REST Client, or similar
• Experience testing web UIs and understanding of cross-browser/cross-environment considerations
• Ability to read and interpret API documentation, data schemas, and system architecture descriptions
• Hands-on experience working on projects that included AI, ML, or NLP components — particularly validating outputs that are probabilistic or context-dependent
• Familiarity with the concept of RAG (Retrieval-Augmented Generation) or LLM-based systems
• Strong analytical thinking — especially the ability to assess whether an AI response is contextually correct, not just technically non-null
• Good understanding of test documentation practices: test plans, test cases, bug reports, traceability