Job description
Job details
- Location: UK
- Work mode: Remote
- Employment type: Freelance (Not an internship)
- Salary: GBP 69,357 per year
Role overview
Mindrift is seeking a Freelance Agent Evaluation Engineer based in the UK to help refine the next generation of AI coding agents. In this project-based role, you will focus on testing and improving AI systems by creating complex, real-world developer tasks and establishing rigorous evaluation criteria to measure model performance.
Job details
This is a Freelance position located in the UK. The role is Remote and is not an Internship. The annual equivalent salary is 69,357 GBP.
Responsibilities
- Develop challenging real-world developer tasks to evaluate AI coding agents
- Define clear and objective evaluation criteria for AI model outputs
- Test AI systems to identify edge cases and performance bottlenecks
- Create high-quality datasets used for training and refining AI models
- Provide detailed technical feedback on model accuracy and efficiency
Requirements
- Strong proficiency in software development and coding best practices
- Professional level of English proficiency for technical documentation
- Experience in testing, evaluating, or improving AI/ML systems
- Ability to simulate complex developer workflows and scenarios
- Proven track record of working independently in a freelance capacity
Benefits
- Flexible remote work environment
- Opportunity to work with leading global tech companies
- Exposure to cutting-edge AI agent technology
- Competitive project-based compensation
Keywords
AI EvaluationLLM TestingCoding AgentsSoftware EngineeringDataset CreationPrompt EngineeringQuality Assurance