💬 Specialized in software quality assurance, I always loved technology and wanted to be part of it. So, I've always been a programming and QA enthusiast 😄.
Currently focused on AI code evaluation — reviewing AI-generated code for correctness, edge cases, and instruction-following gaps.
- Kanban and Scrum methodology;
- Azure DevOps and Trello for project management;
- Adheres to GMUD standards for efficient management processes;
- Recently, integrated Testmo for test planning;
- Gherkin for test scenario creation;
- Manual testing methods;
- Black-box and white-box testing;
- Experience-based, functional, and non-functional testing;
- Mobile testing using Browser Stack and Perfecto;
- API testing with Postman;
- SQL querying;
- React/React Native developer and testing;
I actively use AI tools both in personal projects and in professional QA workflows:
| Tool | How I Use It |
|---|---|
| Claude (Anthropic) | Daily work: writing Jira task comments, technical documentation, code analysis, and structured QA feedback |
| ChatGPT (OpenAI) | Code generation review and prompt testing |
| GitHub Copilot | Evaluating inline code suggestions for accuracy and best practices |
| Gemini (Google) | Code explanation and debugging assistance |
| Perplexity AI | Technical research and documentation |
Beyond using these tools, I also use AI to craft and optimize prompts — and I evaluate their outputs critically, identifying correctness issues, edge case failures, and instruction-following gaps. This hands-on experience with AI-generated content directly supports AI training and code evaluation workflows.
- Logic errors — wrong initialization values, off-by-one errors
- Performance anti-patterns — sequential
awaitinstead ofPromise.all(), O(n²) where better exists - Missing edge cases — null inputs, empty arrays, negative numbers not handled
- Silent failures — exceptions swallowed in catch blocks, returning
undefined - Instruction-following gaps — AI ignoring explicit constraints in the prompt
- Missing documentation — no docstrings, type hints, or input validation
When reviewing AI-generated code, I assess: Correctness · Efficiency · Instruction Following · Edge Cases · Best Practices · Security
📊 2+ AI code reviews documented in Python and JavaScript — see ai-code-review-portfolio
| Project | Description | Stack |
|---|---|---|
| ai-code-review-portfolio | Portfolio of AI-generated code reviews, coding challenges, and bug reports | Python, JavaScript |
| qa-automation-studies | Automated test scripts using Pytest, Selenium, Cypress and API testing | Python, JavaScript |
| estousalvo_RS-CadastroResgatados | Automated registration system for flood rescue victims in RS | Python |
| exercicios-ebac | QA Engineering course exercises at EBAC | Various |
💼 Open to remote QA and AI training opportunities | 📍 Brazil, Rio Grande do Sul