Job Description – Senior SDET (AI Chatbot & Automation) – 6+ Years
Role Overview
We are looking for a Senior SDET with 6+ years of experience in automation testing, API test automation, and AI-powered conversational applications. The ideal candidate should have strong expertise in building scalable automation frameworks and validating AI chatbot behavior, with a solid understanding of the probabilistic nature of AI systems and modern quality engineering practices.
Key Responsibilities
Design, develop, and maintain scalable UI and API automation frameworks. Validate AI chatbot and conversational AI workflows across functional and edge-case scenarios. Test AI responses for relevance, consistency, grounding, and context retention. Design and execute API-first automation for backend and microservices. Develop automated regression suites and integrate them into CI/CD pipelines. Collaborate with Product, Engineering, and AI teams to define effective quality strategies. Perform functional, integration, regression, and end-to-end testing. Analyze failures, perform root cause analysis, and improve automation reliability. Contribute to test planning, test data management, and release quality.
Required Skills & Experience
6+ years of experience in Software Testing / Quality Engineering. Strong hands-on experience in API Automation (Rest Assured, Postman, PyTest, or equivalent). Strong experience in UI Automation using Playwright (preferred), Selenium, or Cypress. Experience testing AI chatbots, conversational AI, or LLM-powered applications. Good understanding of:
Prompt validation Conversational flow testing Context and memory validation AI response evaluation Probabilistic behavior of AI systems (non-deterministic responses) Experience with microservices testing and REST APIs. Strong debugging and root cause analysis skills. Experience with CI/CD pipelines (Jenkins, GitHub Actions, Azure DevOps, etc.). Working knowledge of Agile methodologies and test management tools (JIRA, Azure DevOps, TestRail).
Good to Have
Exposure to RAG-based applications and Agentic AI workflows. Knowledge of AI evaluation concepts such as hallucination detection, response quality, and grounding. Exposure to AI evaluation frameworks (e.g., DeepEval, Ragas, Promptfoo, LangSmith). Experience with cloud platforms (AWS/Azure/GCP). Basic scripting skills in Python or Java.
Key Traits
Strong automation-first mindset. Excellent analytical and problem-solving skills. Ownership and accountability for product quality. Ability to work effectively with cross-functional teams. Good communication and stakeholder collaboration skills. Curiosity to learn and adapt to evolving AI technologies.
Preferred Profile
Candidates with experience testing AI-powered chatbots, virtual assistants, customer support bots, enterprise AI assistants, or conversational AI platforms, combined with strong API and automation engineering experience, will be highly preferred.