DevOps Engineer & AI Model Evaluator for Frontier Coding

Mercor; Oslo; On-site; NOK 4,448,000 - 6,018,000; Full time

Job summary

Mercor partners with a leading AI research lab to support a Frontier Code Agents project. Contributors evaluate frontier AI coding models through structured technical assessments focused on infrastructure engineering workflows and model evaluation.

Role emphasizes reviewing cloud platforms, Kubernetes, CI/CD, observability, and automation while applying engineering judgment to realistic scenarios. Sprint-based work runs 12–24 hour stretches with compensation per accepted task.

Qualifications

• 2+ years of professional DevOps, SRE, or Cloud Engineering experience.
• Experience with AWS, Azure, GCP, Kubernetes, Terraform, CI/CD pipelines, or 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.

Responsibilities

• Use frontier AI coding agents to complete and evaluate complex infrastructure engineering tasks.
• Review model-generated implementations involving cloud platforms, Kubernetes, CI/CD systems, observability, and infrastructure automation.
• Identify bugs, edge cases, reliability issues, and failure modes.
• Compare outputs from multiple frontier models and assess their strengths and weaknesses.
• Apply professional engineering judgment to realistic infrastructure engineering scenarios.

Skills

DevOps experience

Cloud engineering

SRE

Kubernetes

Terraform

CI/CD pipelines

Observability tooling

AI coding agents

Production-scale systems

Tools

AWS

Azure

GCP

Job description

Mercor partners with a leading AI research lab to support a Frontier Code Agents project. Contributors evaluate frontier AI coding models through structured technical assessments focused on infrastructure engineering workflows and model evaluation.

Role emphasizes reviewing cloud platforms, Kubernetes, CI/CD, observability, and automation while applying engineering judgment to realistic scenarios. Sprint-based work runs 12–24 hour stretches with compensation per accepted task.