Freelance AI Evaluation Engineer — Developer Task Architect

Mindrift; Singapore; On-site; SGD 53,000 - 88,000; Full time

Job summary

Mindrift is building a dataset to evaluate AI coding agents by creating realistic developer environments, tasks, and tests. You will craft prompts, define success metrics, and ensure the evaluation is solvable by an AI agent.

You will write tests that accept all valid solutions and iterate based on QA feedback to make the process fair and robust. This role requires 5+ years of software development and strong Python/JS stacks, with English proficiency at least B2+.

Qualifications

• 5+ years in software development.
• Experience writing functional and integration tests.
• English proficiency level: B2+.

Responsibilities

• Create challenging tasks and evaluation criteria within simulated environments.
• Design tasks from intermediate states of these environments and define 'solved' criteria.
• Write tests that accept multiple valid solutions and reject incorrect ones.
• Iterate on tasks and tests based on QA feedback to ensure fairness and robustness.

Skills

5+ years in software development

Tools

Python (FastAPI)

JavaScript/TypeScript (React)

Docker

Postgres

Kafka

Redis

Job description

Mindrift is building a dataset to evaluate AI coding agents by creating realistic developer environments, tasks, and tests. You will craft prompts, define success metrics, and ensure the evaluation is solvable by an AI agent.

You will write tests that accept all valid solutions and iterate based on QA feedback to make the process fair and robust. This role requires 5+ years of software development and strong Python/JS stacks, with English proficiency at least B2+.