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 role, you will focus on testing, evaluating, 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, project-based position located in the UK. The role is Remote and is not an Internship. The offered salary is 69,357 GBP.
Responsibilities
- Develop challenging coding tasks to evaluate the capabilities of AI agents.
- Create detailed evaluation criteria to measure the accuracy of AI-generated code.
- Analyze model outputs to identify failures in real-world developer workflows.
- Contribute to the growth of high-quality datasets for AI training and testing.
- Collaborate with tech teams to improve the reasoning capabilities of AI models.
Requirements
- Strong proficiency in software development and professional coding practices.
- Ability to design complex technical scenarios for AI model stress-testing.
- Professional level of English proficiency for documentation and reporting.
- Experience with AI tools or large language model (LLM) evaluation.
- Ability to work independently in a project-based, freelance environment.
Benefits
- Flexible remote work arrangements.
- Opportunity to work with leading global tech companies.
- Engagement with cutting-edge AI development projects.
Keywords
AI EvaluationLLM TestingCoding AgentsDataset CreationSoftware EngineeringQuality AssurancePrompt Engineering