Software Quality Engineer – Conversational AI / LLM Testing

Job description

Experience: 4-9 Years Location : Noida / Kolkata Domain : Airlines / Travel Technology Job Summary We are seeking a highly skilled Software Quality Engineer with hands-on experience in testing Conversational AI, LLM-based applications, chatbots, virtual assistants, and Agentic AI systems . The ideal candidate will have a strong automation and quality engineering background, deep understanding of how modern conversational systems operate, and solid experience within the Airline or Travel domain , particularly around Booking, Post-Booking, and Check-In workflows . This role involves validating AI-driven customer conversation journeys, ensuring response quality, evaluating non-deterministic outputs, and establishing robust testing strategies for intelligent systems. Key Responsibilities Own and drive the quality strategy for conversational AI products and customer-facing virtual assistants. Design, execute, and automate test scenarios for LLM-powered applications, chatbots, voice assistants, RAG-based systems, and agentic workflows. Validate conversational flows across booking, post-booking servicing, and check-in experiences within airline and travel ecosystems. Develop and maintain automated test frameworks using Python. Create test datasets, golden datasets, and evaluation benchmarks to measure AI system performance. Design evaluation mechanisms for non-deterministic AI outputs using: Rubric-based scoring LLM-as-a-Judge approaches Human review workflows Statistical quality assessment methods Validate prompt behavior, context retention, retrieval accuracy, tool/function calling, and response consistency. Identify conversational AI failure modes such as hallucinations, context loss, prompt injections, retrieval issues, and reasoning errors. Collaborate with Product Managers, Data Scientists, AI Engineers, and Developers to improve system quality and reliability. Participate in release validation, regression testing, performance testing, and production quality monitoring. Mandatory Skills & Qualifications Quality Engineering 4+ years of experience in Software Quality Engineering, QA Automation, or SDET roles. Proven experience owning the quality of a product or platform from testing strategy to production validation. Strong understanding of software testing methodologies, automation frameworks, and quality metrics. Python Automation Strong scripting and automation expertise in Python. Experience developing automated test suites, validation scripts, and data-driven testing frameworks. Conversational AI / LLM Testing Hands-on experience testing one or more of the following: Large Language Model (LLM) applications Conversational AI platforms Chatbots and Virtual Assistants Voice Assistants Retrieval Augmented Generation (RAG) solutions Agentic AI applications AI/LLM Evaluation Expertise Practical understanding of: Prompt engineering principles Context windows and memory handling Function/Tool Calling Retrieval pipelines LLM evaluation methodologies AI quality metrics and benchmarking Experience with: Golden datasets Human evaluation workflows Statistical validation approaches Non-deterministic output testing Domain Knowledge Strong experience in Airline or Travel domain , including: Flight Booking journeys Reservation Management Post-Booking Services Check-In processes Passenger servicing workflows Preferred Skills Experience with OpenAI, Azure OpenAI, Anthropic, Gemini, or similar AI platforms. Understanding of NLP concepts and conversational design. Exposure to API testing and automation tools. Experience with CI/CD pipelines and test automation integration. Knowledge of cloud platforms (Azure, AWS, GCP). Familiarity with observability and monitoring tools for AI applications.