Senior Software Engineer – LLM Evaluation (US/Canada/WEU based)

This contract role asks experienced engineers to help large language models get better at writing code. You would build training datasets and judge solutions the AI produces. It suits senior developers with full-stack depth who like reviewing code critically and explaining their reasoning in writing. The work is for an AI research and training company that supports frontier AI labs.

What you'll do

• Gather code samples, write reference solutions and fix errors in Python, JavaScript (with ReactJS), C/C++, Java, Rust and Go
• Check model-generated code for performance, scalability and reliability
• Build agents and automated checks that confirm whether a coding task was solved correctly and spot recurring mistakes
• Test how well models handle each stage of development, from prototyping and API design through launch and monitoring
• Work with researchers and cross-functional teams

What you'll need

• At least 3 years of professional software engineering
• A record of shipping full-stack, production-grade applications
• A solid grasp of architecture, debugging and code review
• Strong written and spoken communication for structured evaluation notes

Good to know

• Remote contractor role with no medical or paid leave
• Flexible schedule of 10 to 40 hours per week
• Starts as a one-month term and may be extended depending on performance and fit
• Open only to candidates living in the US, Canada or Western European countries
• Applying takes roughly 15-30 minutes and includes an AI video interview