AI Testing Engineer

Undocked; Bengaluru; On-site; INR 800,000 - 1,200,000; Full time

Job summary

A dynamic technology firm is seeking an experienced AI Testing Engineer to join their team in Bengaluru, India. The ideal candidate will have 3+ years of QA or Test Automation experience and strong expertise in Playwright. Responsibilities include designing automation frameworks, testing AI-integrated applications, and ensuring quality and reliability across environments. The role offers an exciting opportunity to validate AI outputs and collaborate with diverse teams in a fast-paced, innovative environment.

Qualifications

• 3+ years of experience in QA or Test Automation.
• Strong hands-on experience with Playwright is mandatory.
• Solid understanding of automation framework design and best practices.

Responsibilities

• Design and maintain automation frameworks using Playwright.
• Develop end-to-end, regression, and API test suites.
• Test AI-integrated features such as recommendation engines and chatbots.
• Validate AI outputs for accuracy, consistency, bias, and edge cases.
• Collaborate with cross-functional teams to define testing strategies.
• Integrate automated tests into CI/CD pipelines.

Skills

QA or Test Automation

Playwright automation expertise

Analytical skills

Problem-solving skills

Agile environments

Tools

Playwright

k6

Job description

At Undocked, we help companies excel in e-commerce by delivering bespoke optimizations and cutting‑edge analytics. Our experience across retail and supply chain product strategy, technology, and operations has helped organizations succeed in their e‑commerce and digital transformation journeys.

As we expand into AI‑enabled systems and intelligent automation, we are looking for an AI Testing Engineer who can ensure quality, reliability, and performance across AI‑driven applications and modern web platforms.

Role Overview

We are seeking a QA professional with strong Playwright automation expertise and hands‑on exposure to AI‑powered systems. You will be responsible for validating intelligent workflows, testing AI‑integrated applications, and ensuring reliability, performance, and accuracy across environments.

This role combines traditional QA rigor with modern AI system validation.

Key Responsibilities

• Design and maintain robust automation frameworks using Playwright
• Develop end‑to‑end, regression, and API test suites
• Test AI‑integrated features such as recommendation engines, chatbots, predictive workflows, or LLM‑based systems
• Validate AI outputs for accuracy, consistency, bias, and edge cases
• Collaborate with product, engineering, and data teams to define test strategies for AI‑driven features
• Perform exploratory and risk‑based testing on intelligent workflows
• Integrate automated tests into CI/CD pipelines
• Contribute to quality standards for AI systems, including prompt testing and model behavior validation

Required Skills

• 3+ years of experience in QA or Test Automation
• Strong hands‑on experience with Playwright (mandatory)
• Solid understanding of automation framework design and best practices
• Experience testing APIs and modern web applications
• Exposure to AI/ML‑powered applications in any of the following areas:
• LLM‑based systems
• Chatbots or conversational AI
• Predictive analytics systems
• Prompt validation and AI output verification
• Strong analytical and problem‑solving skills
• Experience working in Agile environments

Nice to Have

• Experience with k6 for performance and load testing
• Exposure to performance testing concepts
• Familiarity with cloud environments (AWS, Azure, or GCP)
• Experience validating data pipelines or ML workflows
• Understanding of model evaluation metrics