Role Summary
We are looking for a skilled and curious QA Engineer to join our quality engineering team in Hyderabad. The ideal candidate will bring 3–4 years of hands-on experience in manual and automation testing, with strong expertise in Playwright with Python. Beyond traditional QA, you will play a key role in shaping how we test next-generation GenAI-powered applications – designing strategies to evaluate accuracy, reliability, and safety of LLM-based features. You will collaborate closely with developers, data scientists, and product teams to ensure the highest quality across both conventional and AI-driven products.
Key Responsibilities
- Design, write, and execute comprehensive manual test cases across functional, integration, regression, and exploratory testing.
- Build, maintain, and scale automated end-to-end test suites using Playwright with Python.
- Develop and execute test strategies for GenAI applications – including prompt evaluation, response validation, hallucination detection, bias checks, and grounding/retrieval accuracy.
- Define and implement evaluation frameworks for LLM outputs (e.g., golden datasets, rubric-based scoring, similarity metrics, LLM-as-a-judge approaches).
- Integrate automated tests into CI/CD pipelines and contribute to shift-left quality practices.
- Identify, document, and track defects with clear reproduction steps; partner with developers to drive issues to closure.
- Collaborate with product managers, developers, and AI/ML engineers to clarify requirements, identify edge cases, and define acceptance criteria.
- Continuously improve test coverage, reduce flakiness, and report on quality metrics to stakeholders.
- Stay current with emerging tools, frameworks, and best practices in QA automation and GenAI testing.
Required Skills & Experience
- 3–4 years of professional experience in software quality assurance (preferred).
- Strong foundation in manual testing – test case design, execution, defect lifecycle, and reporting.
- Proven hands-on experience with automation testing using Playwright and Python.
- Hands-on experience testing and automating GenAI / LLM-powered applications (chatbots, copilots, RAG systems, agentic workflows, etc.).
- Working knowledge of GenAI concepts: prompts, embeddings, vector search, RAG, agents, model evaluation, and hallucination/safety considerations.
- Solid understanding of QA methodologies, SDLC, STLC, and Agile/Scrum practices.
- Experience with API testing tools (e.g., Postman, REST APIs) and version control (Git).
- Excellent communication skills – ability to clearly articulate issues, collaborate across teams, and present quality insights to technical and non-technical stakeholders.
Nice to Have
- Experience with CI/CD tools (e.g., Jenkins, GitHub Actions, Azure DevOps).
- Exposure to performance testing tools (e.g., JMeter, k6) or security testing basics.
- Experience with cloud platforms (Azure, AWS, or GCP) and containerization (Docker).
- Familiarity with BDD frameworks (e.g., pytest-bdd, Behave).
Soft Skills
- Strong analytical and problem-solving mindset with attention to detail.
- Clear, concise, and proactive communication – both written and verbal.
- Collaborative team player who thrives in cross-functional, fast-paced environments.
- Curiosity and willingness to learn emerging technologies, especially in the GenAI space.
- Ownership mindset and a commitment to quality.
Education
Bachelor's or Master's degree in Computer Science, Engineering, Information Technology, or a related field – or equivalent practical experience.
If you are passionate about quality, excited about the possibilities of GenAI, and enjoy building automation that scales – we'd love to hear from you. 
