About The Role
We are seeking a skilled and proactive SDET to join our team in testing cutting-edge Agentic AI applications. This role requires a strong understanding of both manual testing techniques and automated test frameworks to ensure the reliability, performance, and safety of AI-driven systems. You'll work closely with developers, product managers, and AI researchers to validate intelligent agents, workflows, and user interactions.
Key Responsibilities
- Design and execute manual test cases for AI-driven workflows and agentic behaviors
- Develop and maintain automated test scripts using tools like Selenium, Playwright, Cypress, or similar
- Validate natural language processing (NLP) outputs, agentic decision-making, and multi-step reasoning
- Perform regression, integration, and system testing across web and mobile platforms
- Collaborate with AI/ML engineers to test model outputs, edge cases, and safety boundaries
- Build and maintain CI/CD pipelines for automated test execution
- Analyze test results, identify root causes, and report bugs with clear reproducibility
- Contribute to test strategy, coverage plans, and quality metrics for AI features
- Ensure compliance with ethical AI testing standards, data privacy, and safety guidelines
Required Skills & Experience
- 5+ years of experience in software testing, with at least 1 year in AI or agentic systems
- Proficiency in test automation frameworks (e.g., Selenium, Cypress, Playwright)
- Strong programming skills in Python, JavaScript, or Java
- Experience with REST APIs, GraphQL, and webhooks
- Familiarity with AI/ML concepts, especially LLMs, agentic workflows, and prompt engineering
- Understanding of test design techniques: boundary testing, equivalence partitioning, exploratory testing
- Experience with version control (Git), issue tracking (JIRA), and test management tools (TestRail, Zephyr)
- Knowledge of CI/CD tools like Jenkins, GitHub Actions, or Azure DevOps
- Excellent communication and documentation skills
Preferred Qualifications
- Experience testing Agentic AI platforms, autonomous agents, or multi-agent systems
- Exposure to AI safety, hallucination detection, or prompt validation
- Familiarity with cloud platforms (AWS, Azure, GCP)
- ISTQB or equivalent certification
(ref:hirist.tech)
