Remote Software Engineer for AI Evaluation & RL

Mindmatch; León; A distancia; EUR 71.000 - 178.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Weekly payments

Independent contractor engagement

Descripción de la vacante

MindMatch is seeking a Software Engineer (Remote) to design reinforcement learning environments that evaluate AI models on complex software engineering tasks. You will review AI-generated code, debug and optimize, and build reproducible environments using MCP tools.

The role emphasizes strong software development, distributed systems knowledge, and collaboration with interdisciplinary teams in a fully remote setup.

Formación

• Bachelor's degree or higher in CS/SE/IT or equivalent experience.
• Strong proficiency in Python, C++, Java, Go, TypeScript, Rust, or similar languages.
• Experience with Git, GitHub, debugging, feature implementation, refactoring.
• Understanding of algorithms, data structures, design principles, and performance optimization.
• Excellent analytical thinking and problem-solving skills.
• Strong written and verbal communication with attention to detail.
• Ability to work independently in a fully remote environment.

Responsabilidades

• Design RL environments to evaluate AI models on software tasks.
• Review AI-generated code for correctness and efficiency.
• Debug, add features, refactor, and optimize performance.
• Build reproducible environments using MCP tools.
• Develop and validate deterministic test cases for AI evaluation.
• Contribute to GitHub projects, reviews, and collaboration.
• Document complex concepts for AI training and evaluation.
• Collaborate with cross-functional teams for code quality and accuracy.

Conocimientos

Python

C++

Java

Go

TypeScript

Rust

Git

GitHub

Distributed systems

Debugging

Educación

Bachelor's degree or higher in Computer Science, Software Engineering, IT

Herramientas

Git

GitHub

MCP tools

Descripción del empleo

MindMatch is seeking a Software Engineer (Remote) to design reinforcement learning environments that evaluate AI models on complex software engineering tasks. You will review AI-generated code, debug and optimize, and build reproducible environments using MCP tools.

The role emphasizes strong software development, distributed systems knowledge, and collaboration with interdisciplinary teams in a fully remote setup.