Senior AI-Native Quality Engineer

About Foodhub

Foodhub is a thriving technology company specializing in EPOS and APOS solutions tailored for restaurants and takeaways. Their consumer-centric platform allows customers to effortlessly order meals online through a 0% commission model, leveraging cutting-edge technology, dedicated customer service, and international marketing to support their partners effectively.

Role Overview

We are seeking a Senior AI-Native Quality Engineer (Senior SDET) to revolutionize our software quality practices by integrating AI throughout the testing lifecycle. This hands-on role blends advanced automation skills with practical AI and large language model (LLM) expertise. You will collaborate with Engineering and Product teams in a dynamic and rapid-release environment to increase automation coverage, minimize manual test repetition, and boost regression testing efficiency.

Key Responsibilities

• Architect, develop, and maintain robust automated test frameworks primarily using Playwright and complementary technologies.
• Create automation scripts for web apps, APIs, mobile platforms, and comprehensive user journeys.
• Implement API automation leveraging REST Assured or similar frameworks.
• Develop mobile automation solutions employing Appium as needed.
• Integrate automated test suites within Jenkins and other CI/CD pipelines to establish quality control checkpoints.
• Deliver functional, integration, regression, and end-to-end test automation.
• Identify repetitive manual tests to transition them into automated workflows.
• Optimize test reliability by reducing flaky tests and accelerating execution speeds.
• Engage in requirements gathering, refinement, and release planning to detect potential quality issues early on.
• Analyze failures by reviewing logs, screenshots, and stack traces to support root cause identification.
• Critically evaluate unclear requirements or implementations from a quality and user perspective.

AI-Native Quality Engineering Responsibilities

• Utilize AI to enhance test scenario and case creation.
• Leverage AI for automation coding and debugging support.
• Employ AI for generating synthetic test data and facilitating test maintenance and refactoring.
• Apply AI techniques for regression impact assessment and QA reporting.
• Explore self-healing test mechanisms and intelligent automation strategies.
• Use AI coding assistants to boost automation development efficiency.

AI / LLM Testing Responsibilities

• Evaluate AI features focusing on accuracy, reliability, context management, hallucinations, prompt injection vulnerabilities, adversarial inputs, safety, and boundary conditions.
• Test response quality and robustness.
• Experience with retrieval-augmented generation (RAG), embeddings, vector databases, conversational AI, tool/function calling, and AI agents is highly desirable.
• Understand testing phases including user query, retrieval, context processing, LLM response generation, and response validation.
• Test AI agents for tool selection, invalid parameter handling, state management, and failure recoveries.

Required Skills and Experience

• 5 to 8 years of experience in Software Testing, SDET roles, or Quality Engineering.
• Strong practical experience in test automation.
• Proficient programming skills in Java, TypeScript, or JavaScript.
• Extensive hands-on use of Playwright for automation.
• Robust API automation knowledge with REST Assured or equivalent frameworks.
• Experienced in designing or sustaining automation frameworks.
• Solid understanding of CI/CD pipelines, Git version control, and automated quality gates.
• Expertise in functional, integration, regression, and end-to-end testing methodologies.
• Strong analytical and debugging capabilities.
• Preferred experience with Appium and mobile automation.
• Additional knowledge in Selenium, TestNG/JUnit, SQL, Docker, cloud test execution, performance, or security testing is advantageous.

Mandatory AI Skills

• Practical experience with AI-driven test case and automation generation.
• Competence in AI-assisted debugging, failure analysis, and test maintenance.
• Familiarity with prompt engineering and LLM application testing.
• Experience testing for hallucinations, prompt injection, and AI output quality evaluation.

Preferred AI/LLM Technologies

• Exposure to platforms such as OpenAI, Azure OpenAI, AWS Bedrock, or Gemini.
• Experience with RAG, vector databases, AI agents, and automated LLM evaluation frameworks.

Desired Attributes

• An engineering mindset focused on problem solving beyond mere test execution.
• Active integration of AI tools into daily engineering work.
• Motivation to minimize repetitive manual testing efforts.
• Ability to question assumptions and clarify unclear specifications.
• Ownership of quality outcomes and defect management.
• Strong communication skills with developers and product teams.
• Adaptability to fast-paced Agile product environments.
• Curiosity about modern AI, automation, and quality engineering methodologies.

Additional Details

• Work is onsite in Chennai, India.
• Immediate or short notice availability is preferred.
• The position offers a salary range of ₹2,000,000 to ₹2,500,000 per annum.