Frontier AI DevOps Engineer & Model Evaluator
Summary
Evaluate cutting-edge AI coding models by testing their outputs in cloud, Kubernetes, CI/CD, and observability workflows to spot reliability issues and failure modes.
Mercor is seeking contributors to evaluate frontier AI coding models through structured assessments focused on infrastructure engineering workflows.
You will review model outputs across cloud platforms, Kubernetes, CI/CD, observability, and automation, identifying reliability issues and failure modes. The role emphasizes professional engineering judgment and production-scale evaluation.