QA Automation Engineer / SDET – AI Testing (Mohali)

XenonStack; Mohali; Presencial; INR 600.000 - 1.000.000; Jornada completa

Descripción de la vacante

XenonStack Mohali is seeking a QA Automation Engineer / SDET to join its AI testing team. You will design and implement UI and API test automation using Playwright or Selenium with Python, and build regression suites to run in CI/CD.

You will evaluate LLM and agent behavior, focusing on accuracy, hallucinations, safety and regressions to ensure reliable agentic products. The role requires 2–4 years in test automation, hands-on experience with Playwright or Selenium, Python (Pytest), API testing

Formación

• 2–4 years of experience in test automation.
• Hands-on Playwright or Selenium with Python (Pytest).
• API testing using Postman/REST.

Responsabilidades

• Design and maintain UI and API test automation (Playwright or Selenium, Python, Pytest).
• Build regression suites and run them in CI/CD pipelines.
• Test AI agents and LLM features: evaluate accuracy, hallucinations, safety and prompt regressions.
• Log, track and verify defects; report results to developers and product teams.
• Keep test cases, runbooks and quality metrics current.

Conocimientos

Test automation

Playwright

Selenium

Python (Pytest)

API testing

CI/CD basics

Clear communication

Herramientas

Postman

Git

CI/CD pipelines

Descripción del empleo

QA Automation Engineer / SDET - AI Testing (Mohali)

Location: XenonStack office, STPI, Sector 75, Mohali (Chandigarh Tricity), work from office | Experience: 2-4 years | Full time

ABOUT XENONSTACK

XenonStack is a Data and AI Foundry for Agentic Systems, enabling enterprises to design, deploy, operate and scale intelligent agents. Our platforms: Akira AI (agent orchestration), ElixirData (agentic analytics), NexaStack (agentic infrastructure) and MetaSecure (trust and compliance).

THE ROLE

Testing AI agents is a new kind of quality engineering. You will build test automation with Playwright/Selenium and Python, and learn to evaluate LLM and agent behaviour: accuracy, hallucinations, safety and regressions, so our agentic products are reliable in production.

KEY RESPONSIBILITIES

• Design and maintain UI and API test automation (Playwright or Selenium, Python, Pytest).
  
• Build regression suites and run them in CI/CD pipelines.
  
• Test AI agents and LLM features: build evaluation datasets, check answer accuracy, hallucinations, safety and prompt regressions.
  
• Log, track and verify defects; report clear test results to developers and product teams.
  
• Keep test cases, runbooks and quality metrics current.
  

MUST-HAVE SKILLS

• 2-4 years in test automation.
  
• Hands-on Playwright or Selenium with Python (Pytest).
  
• API testing (Postman, REST).
  
• CI/CD and Git basics.
  
• Clear written communication and ownership.
  

GOOD-TO-HAVE

• Exposure to LLM evaluation tools (DeepEval, Ragas, LangSmith) - we will help you learn.
  
• Performance testing (JMeter, k6).
  
• Docker/Kubernetes and a cloud platform (AWS, Azure or GCP).
  

HOW WE WORK WITH AI

AI is part of the daily workflow at XenonStack. You may use approved AI tools for test design, scripting and documentation, and you verify every AI-assisted output before relying on it.

WHY JOIN US

• Test cutting-edge agentic AI products used by enterprises.
  
• AI-first environment with real ownership.
  
• Great Place to Work-Certified, 14+ years, headquartered in Mohali.