Overview
AI Trainer - Agent Evaluation Infrastructure (MCP) role at Mindrift. We are building Model Context Protocol (MCP) servers and internal tools for running and evaluating agent behavior. You will implement base methods for agent action verification, integrate with internal and client infrastructures, and help fill tooling gaps across the team. Mindrift connects domain experts with AI projects through Toloka to unlock GenAI potential by leveraging real-world expertise.
Responsibilities
- Developing and maintaining MCP-compatible evaluation servers
- Implementing logic to check agent actions against scenario definitions
- Creating or extending tools that writers and QA use to test agents
- Working closely with infrastructure engineers to ensure compatibility
- Occasionally helping with test writing or debug sessions when needed
Qualifications
- 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
- Explicit documentation and communication skills - you'll work with QA and writers
Nice-to-have
- 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
- Ability to support dev environments (devcontainers, CI configs, linters)
- JavaScript experience
Benefits
- Get paid for your expertise, with rates that can go up to $38/hour depending on your skills, experience, and project needs
- Take part in a flexible, remote, freelance project that fits around your commitments
- Participate in an advanced AI project and gain valuable experience for your portfolio
- Influence how future AI models understand and communicate in your field of expertise
Seniority level
- Mid-Senior level
Employment type
- Part-time
Job function
- Other
Industries
- IT Services and IT Consulting
#J-18808-Ljbffr
📌 AI Trainer - Agent Evaluation Infrastructure (MCP)
🏢 Mindrift
📍 Maitland