Design, build and scale testing capabilities using AI agents – using GitHub Copilot Agent Mode on the GitHub Enterprise platform and the Microsoft AI Foundry stack – to automate testing tasks such as test case generation, test data creation, defect triage, and regression analysis.
Develop and run AI evaluation (AI eval) frameworks and metrics to measure the accuracy, reliability, and performance of AI agents and Gen-AI-assisted testing workflows and iterate on prompts and agent design based on eval results.
Write efficient test automation code using coding standards and best practices.
...
Design and build an AI-assisted pipeline that drafts UAT test cases from requirements/user stories (e.g., from Jira/Confluence).
Build agentic execution capability - using Claude to drive through UAT scenarios in a browser or via API, capturing evidence (results, screenshots, traces) rather than requiring a person to click through every flow.
Build regression execution on top of the same pipeline so previously validated UAT scenarios can be re-run automatically against new builds.
...
Design, build and scale testing capabilities using AI agents – using GitHub Copilot Agent Mode on the GitHub Enterprise platform and the Microsoft AI Foundry stack – to automate testing tasks such as test case generation, test data creation, defect triage, and regression analysis.
Develop and run AI evaluation (AI eval) frameworks and metrics to measure the accuracy, reliability, and performance of AI agents and Gen-AI-assisted testing workflows and iterate on prompts and agent design based on eval results.
Write efficient test automation code using coding standards and best practices.
...
Design, build and scale testing capabilities using AI agents, using GitHub Copilot Agent Mode on the GitHub Enterprise platform and the Microsoft AI Foundry stack, to automate testing tasks such as test case generation, test data creation, defect triage, and regression analysis.
Develop and run AI evaluation (AI eval) frameworks and metrics to measure the accuracy, reliability, and performance of AI agents and Gen-AI-assisted testing workflows and iterate on prompts and agent design based on eval results.
Write efficient test automation code using coding standards and best practices.
...
7+ years of experience in software testing ideally within the telecommunications industry?
Educational Background: Bachelor's degree in Information Technology, Computer Science, Engineering, or a related field. A Master’s degree is a plus. • Certification: ISTQB CFTL is preferred. • Experience: 7+ years of experience in software testing ideally within the telecommunications industry. • Skills: o Strong understanding of test management tools (e.g., JIRA, TestRail, ALM). o Excellent knowledge of software testing methodologies and best practices. o Proven leadership and team management abilities. o Strong analytical and problem-solving skills. o Excellent communication and interpersonal skills. o Ability to manage multiple priorities in a fast-paced environment.