Remote Agent Evaluation Engineer: Build-Time Framework

Há 21 horas

Remote, Portugal EPAM Systems Tempo integral

EPAM Systems in Portugal seeks an Agent Evaluation Engineer to design and maintain a build-time evaluation framework for AI agents. You will implement automated tests, staging validations, and deployment gates integrated with production feedback to ensure robustness.

You will develop multi-layer evaluation suites blending deterministic checks with LLM-powered graders, and drive reliability metrics across CI/CD pipelines. This role is fully remote within Portugal.