MCP Expert

Skills

About this role

Experienced software engineers to create Reinforcement Learning environments that evaluate how effectively AI models solve complex software-engineering problems using Model Context Protocol (MCP) tools. The role involves designing realistic coding tasks around debugging, feature implementation, codebase refactoring, and performance optimization while requiring AI agents to interact with real MCP servers. Experts will create reproducible environments, deterministic verification methods, and golden reference solutions that measure both software-engineering quality and effective MCP tool usage. Prior AI experience is not required; strong software-engineering and problem-solving expertise is the primary requirement.

MCP Software Engineering Expert

Responsibilities

• Design reproducible RL environments that test AI agents on complex software-engineering problems using MCP tools.
• Create realistic tasks involving bug fixing, feature implementation, refactoring, algorithms, and performance optimization.
• Develop deterministic validation methods and high-quality golden reference solutions for each task.
• Review technical outputs and contribute to strong engineering, code-review, correctness, and reproducibility standards.

Qualifications

• Strong proficiency in at least one of C++, Python, Java, Go, TypeScript, or Rust.
• Deep understanding of algorithms, data structures, debugging, performance tuning, and scalable software design.
• Demonstrated experience implementing features, resolving complex software issues, and refactoring maintainable production codebases.
• Strong written and verbal communication skills with experience collaborating effectively across technical teams.