AI Coding Agent Evaluator — Build & Benchmark Tasks

Advanced Search; Kuwait City; On-site; KWD 11,000 - 25,000; Full time

Job summary

Mindrift is building a dataset to evaluate AI coding agents by creating realistic developer environments and challenging tasks. The project focuses on testing, evaluating, and improving AI systems and operates on a project-based basis rather than permanent employment.

You will design tasks from simulated environments, write tests to verify agent solutions, and iterate based on QA feedback to ensure fairness and robustness of evaluations.

Qualifications

• 5+ years in software development.
• Experience writing tests (functional, integration).
• Core stack: Python (FastAPI), JavaScript/TypeScript (React), Docker, Postgres, Kafka, Redis.

Responsibilities

• Build realistic developer environments – a virtual company with codebase, infra, and context that forms a believable development history.
• Design tasks from intermediate states of these environments – craft the prompt, define success, ensure solvable by an AI agent.
• Write tests that verify agent solutions—accept all valid approaches and reject incorrect ones.
• Iterate on tasks and tests based on QA feedback and refine until evaluation is fair and robust.

Skills

5+ years dev

Testing experience

Python (FastAPI)

JS/TS (React)

Docker

Postgres

Kafka

Redis

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 and challenging tasks. The project focuses on testing, evaluating, and improving AI systems and operates on a project-based basis rather than permanent employment.

You will design tasks from simulated environments, write tests to verify agent solutions, and iterate based on QA feedback to ensure fairness and robustness of evaluations.