AI Model Evaluation DevOps Engineer
Summary
Builds and maintains cloud infrastructure to evaluate and improve AI coding models using frontier AI agents, debugging and assessing model performance.
Obsidian is seeking contributors for a project partnering with a leading AI research lab. The role involves using frontier AI coding agents to evaluate and improve coding models, focusing on infrastructure engineering tasks. Successful applicants will leverage their experience with cloud platforms and AI tools to identify bugs and assess the strengths of different models.
Compensation is $400 per accepted task, typically taking 2-3 hours to complete. Ideal candidates will have 2+ years of relevant experience in DevOps or Cloud Engineering.