About the role
Responsibilities:
- Perform manual and functional testing of web applications, workflows, and Reinforcement Learning (RL) environments.
- Design, execute, and maintain detailed test cases and test scenarios covering functional, regression, exploratory, and negative testing.
- Validate task prompts, expected outcomes, and automated evaluation/grader logic for accuracy and consistency.
- Identify false positives and false negatives by comparing actual application behavior against expected results.
- Test end-to-end workflows, edge cases, boundary conditions, unexpected inputs, and different user scenarios.
- Verify that application and environment states match the expected outcomes after task execution.
- Identify, document, and track defects with clear reproduction steps, expected vs. actual behavior, screenshots/logs, and appropriate severity.
- Work closely with developers, product teams, and AI/research teams to investigate issues and ensure timely resolution.
- Participate in requirement reviews and identify gaps, ambiguities, and missing test scenarios before implementation or release.
- Perform regression testing and validate fixes across multiple release cycles.
- Maintain QA documentation, test results, and release sign-off details using tools such as Jira, GitHub, or Google Sheets.
- Contribute to improving testing processes and quality standards in a fast-paced AI product environment.
- Work from the Bengaluru office as required and collaborate closely with cross-functional teams.