What You'll Be DoingDeveloping and maintaining MCP-compatible evaluation serversImplementing logic to check agent actions against scenario definitionsCreating or extending tools that writers and QAs use to test agentsWorking closely with infrastructure engineers to ensure compatibilityOccasionally helping with test writing or debug sessions when neededRequirements4+ years of Python development experience, ideally in backend or toolsSolid experience building APIs, testing frameworks, or protocol-based interfacesUnderstanding of Docker, Linux CLI, and HTTP-based communicationAbility to integrate new tools into existing infrastructuresFamiliarity with how LLM agents are prompted, executed, and evaluatedClear documentation and communication skills – you'll work with QA and writersWe Also Value Applicants Who HaveExperience with Model Context Protocol (MCP) or similar structured agent-server interfacesKnowledge of FastAPI or similar async web frameworksExperience working with LLM logs, scoring functions, or sandbox environmentsAbility to support dev environments (devcontainers, CI configs, linters)JS experienceBenefitsGet paid for your expertise, with rates that can go up to $80/hour depending on your skills, experience, and project needsTake part in a flexible, remote, freelance project that fits around your primary professional or academic commitmentsParticipate in an advanced AI project and gain valuable experience to enhance your portfolioInfluence how future AI models understand and communicate in your field of expertiseJ-18808-Ljbffr. About The ProjectWe're on the hunt for hands-on Python engineers for a new project focused on developing Model Context Protocol (MCP) servers and internal tools for running and evaluating agent behavior.