Senior Software Engineer – Reinforcement Learning Environments (Remote)

About the role

We are looking for a senior software engineer to design and build reinforcement‑learning environments that evaluate AI models on real‑world software engineering tasks. The role is fully remote and contract‑based, allowing you to contribute 15 hours per week while shaping next‑generation AI training pipelines.

Key responsibilities

• Create deterministic reinforcement‑learning environments that test bug fixing, feature implementation, refactoring, and performance optimisation.
• Develop golden‑reference solutions and verification suites to measure tool usage and engineering ability.
• Collaborate with cross‑functional teams to ensure reproducibility and scalability of test environments.
• Document environment specifications and provide clear guidance for AI agents interacting with Model Context Protocol (MCP) servers.

Required profile

• Senior‑level software engineering experience with a strong focus on algorithmic problem solving.
• Proven ability to debug complex codebases and deliver maintainable, high‑performance solutions.
• Excellent written and verbal communication skills, especially for remote collaboration.

Required skills

• C++
• Python
• Java
• Go (GoLang)
• TypeScript
• Rust
• Algorithms and data structures
• Performance tuning and optimisation

What we offer

• Output‑based compensation paid per completed task.
• Flexible remote work schedule.
• Opportunity to influence cutting‑edge AI training methodologies.