Junior Software Test Automation Engineer (Client: Uber) — AI model evaluation framework development
Developed automated evaluation frameworks to benchmark AI models and generate structured, actionable feedback for engineering stakeholders. The work focused on assessing model behavior and supporting iterative improvements based on evaluation outputs. Responsibilities also included debugging and verification activities tied to production-quality code and test logic.• Built evaluation tooling to benchmark AI models and report performance insights.• Applied root-cause analysis to investigate logical errors in complex test cases.• Worked on CI/CD-related quality improvements by migrating legacy test suites.• Collaborated with developers to resolve failures and improve coverage across high-scale services.
2024 - 2025