Senior Playwright Automation Engineer

GSPANN Technologies, Inc.; Hyderabad; On-site; INR 1,200,000 - 2,000,000; Full time

Job summary

GSPANN Technologies, Inc. is seeking a Senior Playwright Automation Engineer to design scalable test automation frameworks and validate Generative AI and Agentic AI applications.

You will focus on advanced testing strategies for AI systems and ensure robust quality across UI, API, and end-to-end workflows. Responsibilities include building reusable automation frameworks, integrating tests into CI/CD pipelines, and validating AI components such as LLMs, chatbots, copilots, and RAG-based systems.

Qualifications

• 8+ years in Software QA, test automation, and quality engineering.

Responsibilities

• Automate UI, API, integration, regression, smoke, and end-to-end tests.
• Build reusable frameworks with POM, fixtures, and utilities.
• Integrate tests into CI/CD pipelines (Jenkins, Azure DevOps, GitHub Actions, GitLab).
• Validate Gen AI-powered apps including LLMs, chatbots, copilots, and RAG-based systems.
• Design test strategies for prompt validation, hallucination detection, bias, and safety testing.
• Test Agentic AI workflows with multi-agent orchestration and autonomous decision-making.
• Create evaluation metrics for AI quality, latency, and reliability.
• Test AI integrations with enterprise apps, databases, and third-party services.

Skills

Playwright

UI Automation

API Automation

CI/CD

REST API testing

POM design

Test Frameworks

Git workflows

Gen AI testing

LLM evaluation

Tools

Jenkins

Azure DevOps

GitHub Actions

Git

Job description

Description

GSPANN is hiring a Senior Playwright Automation Engineer to design scalable test automation frameworks and validate Generative AI and Agentic AI applications, focusing on advanced testing strategies for AI systems.

Roles and Responsibilities

• Automate UI, API, integration, regression, smoke, and end-to-end testing scenarios.
• Build reusable frameworks leveraging Page Object Model (POM), fixtures, and custom utilities.
• Perform API automation testing for Representational State Transfer (REST) and microservices-based applications.
• Integrate automated test execution into Continuous Integration / Continuous Delivery (CI/CD) pipelines.
• Validate Generative AI-powered applications including Large Language Models (LLMs), chatbots, copilots, AI agents, and Retrieval Augmented Generation (RAG)-based systems.
• Design test strategies for prompt validation, response accuracy, hallucination detection, toxicity, bias, guardrails, and safety testing.
• Develop automated validation frameworks for AI-generated outputs.
• Test Agentic AI workflows involving multi-agent orchestration, planning, tool usage, and autonomous decision-making.
• Validate AI integrations with enterprise applications, APIs, databases, and third-party services.
• Create evaluation metrics for AI quality, relevance, consistency, latency, and reliability.
• Implement automated testing for AI workflows using Playwright, APIs, and AI evaluation frameworks.

Skills and Experience

• Bring 8+ years of experience in Software Quality Assurance, Test Automation, and Quality Engineering.
• Apply proven expertise in UI, API, integration, regression, smoke, and end-to-end test automation.
• Work with experience designing, developing, and maintaining scalable automation frameworks from scratch using industry-standard design patterns such as Page Object Model (POM) and reusable test components.
• Develop strong experience in Representational State Transfer (REST) API testing, microservices testing, and API automation using Playwright and related tools.
• Manage hands-on experience integrating automated test suites with Continuous Integration / Continuous Delivery (CI/CD) pipelines using Jenkins, Microsoft Azure DevOps, GitHub Actions, or GitLab CI.
• Utilize practical experience with source control systems such as Git and Agile and Scrum delivery methodologies.
• Bring experience testing Generative Artificial Intelligence (Gen AI) applications, including Large Language Model (LLM)-based chatbots, AI assistants, copilots, and conversational AI platforms.
• Demonstrate strong understanding of Prompt Engineering, Large Language Model (LLM) evaluation, Retrieval Augmented Generation (RAG), AI response validation, hallucination detection, AI safety, responsible AI, and guardrail testing.
• Apply experience validating Agentic AI systems, including multi-agent workflows, autonomous decision-making, planning, tool orchestration, and agent-to-agent interactions.