• Planejar, elaborar e executar testes funcionais e automatizados; • Criar cenários e casos de teste com base em requisitos funcionais e critérios de aceite; • Identificar, registrar, acompanhar e validar correções de bugs; • Garantir a qualidade das entregas realizadas pelo time de desenvolvimento; • Participar ativamente de cerimônias ágeis, como daily, planning, review e retrospectiva; • Desenvolver e manter automações de testes; • Apoiar na definição de critérios de qualidade e aceite das entregas; • Elaborar reports de testes e análises de qualidade; • Atuar de forma colaborativa na melhoria contínua dos processos de QA e desenvolvimento.

• Define, execute, and continuously improve quality assurance standards for AI agent and prompt outputs, ensuring generated responses meet expectations for accuracy, consistency, completeness, and explainability. • Oversee QA activities throughout the AI lifecycle, including pre‑deployment validation and post‑deployment output monitoring (regression testing). • Ensure AI outputs support informed decision-making by validating clarity, applicability, and alignment with intended business value. • Serve as an advocate for high-quality AI outputs, promoting shared understanding of output standards and expectations across the organization. • Lead and oversee QA Analysts responsible for reviewing and evaluating AI agent and prompt outputs. • Provide direction, coaching, and prioritization to ensure consistent application of output QA standards and timely completion of QA activities. • Forecast QA timelines and capacity in coordination with AI leadership to support delivery commitments and ensure deadlines are met. • Coordinate cross team to align QA activities with delivery timelines and ensure prompt and agent readiness. • Assist with the development of repeatable AI output evaluation approaches that can be applied across use cases to drive efficiency and consistency. • Document QA findings, trends, and recurring issues related to AI agent and prompt outputs. • Prepare reports, summaries, and presentations for management outlining QA results, risks, and improvement opportunities. • Identify opportunities to improve QA processes, tools, and standards based on observed output behavior and delivery feedback.

• Execute manual regression test scripts across release candidates, covering new features and existing functionality • Validate functionality across a broad range of application modules, workflows, and user roles • Perform smoke testing, feature testing, and onboarding regression validation • Apply boundary and negative testing techniques to validate data integrity, edge cases, and error handling — particularly important for engineering data inputs and threshold-driven calculations • Test against multiple client configurations and environments • Support the development and execution of API and integration test cases as the team expands its testing coverage • Log defects in Azure DevOps with clear reproduction steps, screenshots, and test data • Triage and validate bug fixes; conduct regression on resolved defects • Leverage Azure App Insights to capture additional error context where applicable • Communicate clearly with developers to ensure defects are well-understood and actionable • Create, update, and organize test cases and test suites within Azure DevOps • Maintain the Master Test Script List as new features and modules are released • Contribute to the Functional, Onboarding, and CIM Smoke Regression suites • Collaborate with developers, product managers, and the QA Manager to align on priorities and release readiness • Provide QA status updates and escalate risks to the QA Manager in a timely manner

• Modelar, elaborar e executar testes funcionais, regressivos, exploratórios; • Levantar os critérios de aceite baseados nas regras de negócio das histórias de negócio; • Vivência em metodologias ágeis (Scrum/Kanban); • Versionamento de código fonte de automação de casos de testes; • Execução e geração de evidência de execução de testes manuais/automatizados; • Elaboração relatórios de resultados de testes planejados versus testes realizados para a gestão; • Geração de massa de dados para testes