MCP & Tools Python Developer - Agent Evaluation Infrastructure

Mindrift is seeking Python developers to develop Model Context Protocol (MCP) servers and tools for evaluating agent behavior. The role involves building and maintaining evaluation servers, implementing agent action verification logic, and integrating with internal and client infrastructures. They are looking for security researchers, engineers, and penetration testers with a strong problem-solving and AI-related risk assessment background.

Requirements

• 4+ years of Python development experience, ideally in backend or tools
• Solid experience building APIs, testing frameworks, or protocol-based interfaces
• Understanding of Docker, Linux CLI, and HTTP-based communication
• Ability to integrate new tools into existing infrastructures
• Familiarity with how LLM agents are prompted, executed, and evaluated
• Clear documentation and communication skills
• Experience with Model Context Protocol (MCP) or similar structured agent-server interfaces
• Knowledge of FastAPI or similar async web frameworks
• Experience working with LLM logs, scoring functions, or sandbox environments
• Experience with devcontainers, CI configs, linters
• JS experience

Benefits

• Competitive hourly rate
• Flexible, remote, freelance project
• AI project experience
• Portfolio enhancement
• Influence future AI models