DevOps Engineer for AI Model Evaluation

This role supports a Frontier Code Agents initiative at a leading AI research lab, focused on evaluating and improving advanced AI coding models by performing structured technical assessments of realistic infrastructure engineering workflows and model outputs.

• Use frontier AI coding agents to perform and evaluate complex infrastructure engineering tasks.
• Review model-generated implementations that involve cloud platforms, Kubernetes, CI/CD systems, observability, and infrastructure automation.
• Identify bugs, edge cases, reliability problems, and likely failure modes in model outputs.
• Compare outputs from multiple frontier models, assessing relative strengths and weaknesses.
• Apply professional engineering judgment to realistic infrastructure and reliability engineering scenarios.

• Minimum 2 years of professional experience in DevOps, SRE, or Cloud Engineering.
• Hands-on experience with one or more cloud platforms, such as AWS, Azure, or GCP.
• Familiarity with Kubernetes, Terraform, CI/CD pipelines, and observability tooling.
• Regular use of AI coding agents such as Cursor, Claude Code, Codex, Windsurf, Gemini CLI, or similar tools.
• Ability to evaluate model-generated infrastructure and reliability engineering solutions.
• Experience supporting production-scale systems is preferred.

• Remote role.
• Hourly engagement, sprint based, with project sprints running in 12 to 24 hour stretches depending on client requirements.
• Spots are limited and are filled on a first come, first serve basis.

• $400 paid per accepted task.
• Typical tasks take approximately 2 to 3 hours of work after ramp-up.
• Compensation is tied to accepted work.
• Metadata indicates an hourly reference rate of $85 per hour.

• Role is open to remote applicants. No specific work authorization or sponsorship information was provided in the source; applicants should confirm they are eligible to work in their location.