We are seeking an experienced SDET – Automation with 2 to 4 years of hands-on experience in building scalable automation solutions and a solid interest or experience in Generative AI–driven testing approaches. The ideal candidate combines solid engineering fundamentals with modern QA practices, including AI-assisted test design, validation, and quality engineering in Agile environments.

Key Responsibilities

- Design, develop, and maintain robust automation frameworks for Web, API, and Mobile applications

- Build and execute end-to-end automated test suites covering functional, regression, and integration scenarios

- Apply GenAI techniques to improve test coverage, test data generation, and exploratory testing

- Validate AI/ML-powered features, including GenAI outputs for accuracy, relevance, bias, and consistency

- Collaborate with developers, product, data, and DevOps teams to ensure quality across SDLC

- Automate API and backend testing including validation of data pipelines and services

- Integrate automation with CI/CD pipelines and ensure reliable test execution

- Analyze failures, identify root causes, and drive defect resolution (with GenAI is a plus here)

- Contribute to test strategy, quality metrics, and release readiness





Required Skills & Qualifications

Experience

- 6–8 years of experience in Automation Testing / SDET roles

- Proven experience building or enhancing automation frameworks from scratch

Programming & Automation

- Strong coding skills in Java / Python / JavaScript

- Hands-on experience with Selenium / Playwright / Cypress

- Experience with API automation using RestAssured / Postman / Karate

- Strong understanding of OOP, data structures, and design patterns

Generative AI / AI Testing

- Working knowledge of Generative AI concepts (LLMs, prompts, embeddings, hallucinations, evaluation metrics)

- Experience with Claude-Code is advantage

- Experience testing GenAI-enabled features such as chatbots, summarization, recommendation, or content generation

- Hands-on exposure to prompt engineering, prompt versioning, and prompt evaluation

- Experience validating LLM outputs for correctness, relevance, safety, bias, and determinism

- Familiarity with LLM APIs (e.g., OpenAI, Azure OpenAI, or similar)

- Understanding of AI testing strategies including golden datasets, synthetic data generation, and regression testing for AI models

📌 Software Engineer in Test (Bengaluru)
🏢 LivSpace
📍 Bengaluru