Job description
Job details
- Location: UK
- Work mode: Remote
- Employment type: Freelance (Not an internship)
- Salary: GBP 77,221 per year
Role overview
Mindrift is seeking a Freelance Agent Evaluation Engineer to help build datasets that evaluate AI coding agents and their ability to handle real-world developer tasks. This project-based opportunity involves creating challenging tasks and evaluation criteria for leading tech companies focused on testing and improving AI systems. The role is remote and available across the UK, offering freelance flexibility for specialists with strong coding and AI evaluation experience.
Job details
Location: UK (Remote) Type: Freelance, project-based engagement Salary: £77,221 GBP Requirements: CV must be submitted in English with English proficiency level indicated
This is not a permanent employment position but a project-based opportunity to work with cutting-edge AI evaluation systems.
Responsibilities
- Create challenging tasks to evaluate AI coding agent performance
- Develop evaluation criteria for real-world developer scenarios
- Test and assess AI model capabilities on coding tasks
- Build datasets for AI system improvement and benchmarking
- Collaborate with tech companies on AI evaluation projects
Requirements
- Strong coding experience in Python or similar languages
- Understanding of AI systems and machine learning models
- Fluent English proficiency (written and spoken)
- Experience with software testing or quality assurance
- Ability to design realistic developer task scenarios
- Self-directed work style suitable for project-based engagement
Benefits
- Competitive freelance rate of £77,221
- Fully remote work from anywhere in the UK
- Flexible project-based schedule
- Work with leading tech companies on AI innovation