AI Model Evaluation DevOps Engineer
Summary
Builds and runs realistic DevOps workflows to evaluate and improve AI coding models for a frontier code-agent project.
Obsidian is seeking contributors to work on a Frontier Code Agents project, evaluating and improving AI coding models through technical assessments. This role focuses on realistic infrastructure workflows.
Ideal candidates should have experience in DevOps, SRE, or Cloud Engineering, plus a strong grasp of tools like AWS and Kubernetes. Compensation is task-based, with $400 per accepted task, typically requiring 2-3 hours to complete.