Job description
Job details
- Location: Birmingham, West Midlands
- Work mode: Remote
- Employment type: Freelance (Not an internship)
- Salary: GBP 75,154 per year
Role overview
Mindrift is seeking a Freelance Agent Evaluation Engineer to work on project-based AI opportunities in Birmingham, West Midlands. This freelance role focuses on testing, evaluating, and improving AI coding agents for leading tech companies. You will create challenging tasks and evaluation criteria to assess how well AI models handle real-world developer workflows. The position offers £75,154 and is a contract opportunity, not permanent employment.
Job details
This is a freelance, contract position based in Birmingham, West Midlands, operating on a remote or hybrid basis. The role is project-based, connecting specialists with AI evaluation work. Candidates must submit their CV in English and indicate their English proficiency level. Compensation is £75,154 GBP. You will build datasets to evaluate AI coding agents and define benchmarks for model performance in realistic development scenarios.
Responsibilities
- Create challenging tasks to evaluate AI coding agent performance
- Define evaluation criteria for real-world developer workflows
- Build datasets to test and benchmark AI model capabilities
- Assess how well AI systems handle practical coding scenarios
- Collaborate with tech companies on project-based AI improvements
Requirements
- Strong English proficiency (written and spoken)
- Experience with AI systems, machine learning, or software testing
- Understanding of developer workflows and coding tasks
- Ability to design realistic evaluation benchmarks
- Self-directed work style suitable for freelance projects
Benefits
- Competitive freelance rate of £75,154
- Flexible project-based engagement
- Work with leading tech companies
- Remote or hybrid work options