AI Test Engineer / SDET - AI Enablement Platform

Mployee.me; Bengaluru; Sur place; INR 1 500 000 - 4 000 000; Plein temps

Résumé du poste

Mployee.me is seeking a highly skilled AI Test Engineer / SDET to drive quality for our AI Enablement Platform. You will validate AI-powered agents, GenAI artifacts, and AI-driven testing solutions across UI, API, ETL, and data workflows.

This role combines Quality Engineering, Test Automation, and AI Validation, requiring expertise in automation frameworks, AI agent testing, test orchestration, and CI/CD quality practices.

Qualifications

• Experience testing AI/GenAI systems and validating AI artifacts.
• Proficient in AI agent testing, prompt validation, and LLM evaluation.
• Strong automation skills across UI, API, and data pipelines.
• Familiar with CI/CD integration and governance in AI contexts.

Responsabilités

• Validate AI-powered agents across SDLC workflows.
• Test AI-generated requirements, test cases, scripts, and code artifacts.
• Perform AI agent validation, prompt testing, hallucination detection, and output verification.
• Develop and maintain scalable automation frameworks for UI, API, ETL, and data validation.

Connaissances

AI Testing / GenAI Testing

AI Agent Validation

LLM Output Validation

Prompt Testing & Response Validation

GitHub Copilot / Microsoft Copilot

AI-Assisted SDLC Validation

Playwright

Selenium

API Testing (Postman / REST Assured)

Python

Java

SQL

Automation Framework Development

Functional, Regression & End-to-End T

CI/CD Quality Assurance

Agile Methodologies

Description du poste

We are seeking a highly skilled AI Test Engineer / SDET to drive quality assurance for our AI Enablement Platform. The ideal candidate will be responsible for validating AI-powered agents, GenAI-generated artifacts, and AI-driven testing solutions across UI, API, ETL, Data Validation, and Event-Driven applications.

This role combines Quality Engineering, Test Automation, and AI Validation, requiring expertise in automation frameworks, AI agent testing, test orchestration, and CI/CD quality practices.

Key Responsibilities

AI & GenAI Testing (Primary Focus)

• Validate and test AI-powered agents across SDLC workflows.
• Assess the quality, accuracy, consistency, and reliability of AI-generated requirements, test cases, automation scripts, and code artifacts.
• Perform AI Agent Validation, prompt testing, hallucination detection, response quality assessment, and output verification.
• Evaluate and improve the effectiveness of Agentic AI workflows and AI-assisted engineering solutions.
• Support adoption and governance of GitHub Copilot, Microsoft Copilot, and GenAI-enabled development practices.

Quality Engineering & Automation

• Develop and maintain scalable automation frameworks for UI, API, ETL, Data Validation, and Kafka applications.
• Execute Functional, Integration, Regression, and End-to-End testing.
• Implement automated validation within CI/CD pipelines.
• Perform defect analysis, root cause analysis, and quality reporting.
• Ensure compliance, traceability, governance, and quality standards across AI-enabled solutions.

Mandatory Skills

AI / GenAI Skills (High Priority)

• AI Testing / GenAI Testing
• AI Agent Validation
• LLM Output Validation
• Prompt Testing & Response Validation
• GitHub Copilot / Microsoft Copilot
• AI-Assisted SDLC Validation

Automation & QA Skills

• Playwright or Selenium
• API Testing (Postman / REST Assured)
• Python or Java
• SQL
• Automation Framework Development
• Functional, Regression & End-to-End Testing
• CI/CD Quality Assurance
• Agile Methodologies

Good to Have

• Agentic AI Frameworks
• Retrieval-Augmented Generation (RAG) Testing
• LLM Evaluation Frameworks
• Kafka/Event-Driven Testing
• ETL/Data Validation Testing
• Azure OpenAI Services
• AI Governance & Responsible AI Testing