Job description
Job details
- Location: London, UK
- Work mode: Remote
- Employment type: Freelance (Not an internship)
- Salary: GBP 71,783 per year
Role overview
Mindrift is seeking a Freelance Agent Evaluation Engineer based in London, UK, to help refine the capabilities of AI coding agents. In this role, you will contribute to the development of high-quality datasets used to test how AI models handle complex, real-world developer tasks. This is a project-based freelance opportunity designed for specialists who can bridge the gap between software engineering and AI evaluation.
Job details
This is a Freelance position located in London, UK, operating on a Remote basis. This is not an Internship. The compensation for this project-based engagement is GBP 71,783.
Responsibilities
- Develop challenging real-world coding tasks to evaluate AI agent performance
- Create detailed evaluation criteria and benchmarks for AI-generated code
- Analyze model outputs to identify edge cases and failure modes in AI coding
- Collaborate with AI researchers to improve the accuracy of coding models
- Document test cases and expected outcomes for complex developer workflows
Requirements
- Proven experience in software development and professional coding practices
- Strong proficiency in English, both written and verbal
- Ability to design complex technical scenarios for AI testing
- Analytical mindset with a focus on precision and technical accuracy
- Experience with AI tools or LLM evaluation is highly preferred
Benefits
- Flexible freelance project-based engagement
- Opportunity to work with leading global tech companies
- Remote work flexibility
- Competitive project compensation
Keywords
AI EvaluationLLM TestingSoftware EngineeringDataset CreationCoding AgentsPythonQuality AssurancePrompt Engineering