Description

Key Responsibilities

• Design, develop, and execute automated test cases for AI Agents and Agentic AI applications.
• Test Salesforce Agentforce agents and other AI/LLM-based agents for functionality, reliability, and expected behavior.
• Develop automation frameworks and test scripts for agent workflows, tools, integrations, and end-to-end scenarios.
• Validate AI agent responses, tool/function calling, workflows, prompts, and expected outcomes.
• Perform functional, regression, integration, and end-to-end testing of AI-powered applications.
• Identify and troubleshoot defects related to agent behavior, integrations, workflows, and automation.
• Work with developers, QA engineers, and product teams to define test strategies and acceptance criteria for AI features.
• Use modern AI-assisted development and testing tools such as Cursor, Claude, GitHub Copilot, or similar platforms.
• Create and maintain automated regression suites.
• Document test results, defects, test scenarios, and automation coverage.
• Contribute to improving QA processes and automation practices for AI-based applications.

Required Skills

• 2+ years of hands-on experience with Agentic AI / AI Agents / LLM-based applications.
• Experience testing or automating Salesforce Agentforce or similar AI agent platforms.
• Experience with QA automation and automated testing frameworks.
• Understanding of LLMs, prompts, AI agent workflows, tools/function calling, and AI application testing.
• Strong understanding of software QA fundamentals, including functional, regression, integration, and end-to-end testing.
• Ability to create test scenarios for non-deterministic AI/LLM-based applications.
• Good analytical, troubleshooting, and communication skills

Key Skills

Education

Bachelor's degree