AI Model Evaluation DevOps Engineer
Summary
Evaluates and improves frontier AI coding models by running DevOps tasks with AI agents and reviewing generated code in AWS/Kubernetes environments.
Obsidian is seeking professionals to assess and improve frontier AI coding models as part of a project with a leading AI research lab. The role involves evaluating complex infrastructure engineering tasks using AI agents and reviewing model-generated implementations.
Applicants should have over 2 years of experience in DevOps or Cloud Engineering and proficiency in tools like AWS, Kubernetes, and CI/CD systems. Each accepted task is compensated at $400.