AI Tester (Playwright Automation)

Job Description: AI Tester (Playwright Automation)

Experience: 3 to 6 Years
Employment Type: Full-Time
Location: On-Site
Product: PRMAI AI-First Procurement SaaS Platform
Department: Quality Engineering
Reporting To: Head of Quality Engineering

About PRMAI

PRMAI is an AI-first procurement platform built to transform enterprise sourcing, supplier intelligence, contract lifecycle management, and spend analytics. Leveraging Generative AI, Machine Learning, and advanced automation, PRMAI empowers procurement teams to make faster, smarter, and more strategic decisions.

As we continue to expand our AI capabilities, we are looking for an experienced AI Tester with strong Playwright automation expertise to ensure the quality, reliability, and performance of our AI-driven features and enterprise SaaS applications.

Job Overview

We are seeking a highly skilled AI Tester with 36 years of experience in software testing and automation, including hands-on expertise in Playwright and modern testing practices. The ideal candidate will be responsible for validating both conventional application functionality and AI-powered features, ensuring accuracy, reliability, security, and exceptional user experience.

This role requires a strong understanding of automation frameworks, API testing, data validation, AI output verification, and cloud-native applications. The candidate will work closely with Product Managers, Developers, AI Engineers, and DevOps teams to embed quality throughout the software development lifecycle.

Key Responsibilities

AI Feature Testing

• Design and execute comprehensive test strategies for AI-powered modules and workflows.
• Validate AI-generated outputs for accuracy, consistency, reliability, and business relevance.
• Develop test scenarios covering edge cases, ambiguous inputs, and exception handling.
• Perform validation of AI model responses, recommendations, classifications, and predictive outputs.
• Collaborate with AI and product teams to define measurable quality benchmarks for AI-driven features.

Automation Testing

• Develop, maintain, and enhance automated test suites using Playwright with TypeScript or JavaScript.
• Create scalable automation frameworks supporting UI, API, and end-to-end testing.
• Implement reusable Page Object Models (POM), utilities, and test data management practices.
• Perform cross-browser and cross-platform testing using Playwright.
• Improve test coverage while reducing execution time and maintenance effort.

API & Backend Validation

• Validate REST and GraphQL APIs for functionality, performance, security, and reliability.
• Perform schema validation, response verification, and negative testing.
• Execute data validation using SQL queries across application databases.
• Verify end-to-end data flow across integrated systems and AI services.

Quality Engineering & Continuous Testing

• Integrate automated test suites into CI/CD pipelines.
• Participate in sprint planning, requirement reviews, and design discussions.
• Conduct regression, smoke, sanity, integration, and system testing activities.
• Analyze defects, perform root cause analysis, and collaborate with development teams on resolutions.
• Maintain test reports, dashboards, and quality metrics.

Performance & Reliability Testing

• Support performance and load testing initiatives for AI-enabled applications.
• Validate system behavior under high-volume and peak-load conditions.
• Monitor application quality trends and proactively identify risks.

Key Skills

Must-Have Technical Skills

Automation & Testing

• Strong hands-on experience with Playwright Automation.
• Proficiency in TypeScript and/or JavaScript.
• Experience designing and maintaining automation frameworks.
• Expertise in UI, API, Regression, Integration, and End-to-End Testing.
• Strong understanding of test design patterns including Page Object Model (POM).

AI Testing

• Experience testing AI/ML-enabled applications or intelligent software features.

• Understanding of AI testing concepts such as:

• Output validation
• Hallucination detection
• Bias assessment
• Response consistency
• Prompt testing

• Model behavior validation

• Familiarity with Generative AI and Large Language Models (LLMs).

API & Data Testing

• Strong experience in REST API testing.
• Knowledge of GraphQL testing.
• Hands-on experience with Postman or similar API testing to…