Agent Evaluation Engineer

Explore more jobs; Kuwait City; On-site; KWD 17,000 - 21,000; Full time

Job summary

Mindrift connects specialists with project-based AI opportunities for leading tech companies. You will build datasets to evaluate AI coding agents, design tasks from realistic environments, and write tests that accept multiple valid solutions while rejecting incorrect ones.

The role is project-based, not permanent employment, and involves reviewing agent solutions, analyzing failures, and iterating until evaluation is fair and robust.

Qualifications

• 5+ years in software development.
• Core stack includes Python (FastAPI), JS/TS (React), Docker, Postgres, Kafka and Redis.
• Experience writing tests (functional, integration).
• English proficiency at least B2+.

Responsibilities

• Design tasks and evaluation criteria for AI coding agents within simulated environments.
• Write tests that verify agent solutions and ensure fairness.
• Review agent solutions, analyze failures, and iterate to improve task robustness.

Skills

Software development

Testing / QA

English proficiency

Tools

Python (FastAPI)

JavaScript/TypeScript (React)

Docker

Postgres

Kafka

Redis

Job description

Description

Please submit your CV in English and indicate your level of English proficiency.

Mindrift connects specialists with project-based AI opportunities for leading tech companies, focused on testing, evaluating, and improving AI systems. Participation is project-based, not permanent employment.

What this opportunity involves

We're building a dataset to evaluate AI coding agents - how well a model handles real-world developer tasks.

You'll create challenging tasks and evaluation criteria within realistic simulated environments:

• Build realistic developer environments - a virtual company with codebase, infrastructure, and context (tickets, docs, conversations) that forms a believable development history


• Design tasks from intermediate states of these environments - craft the prompt, define what \"solved\" means, and ensure the task is solvable by an AI agent


• Write tests that verify agent solutions - accept all valid approaches and reject incorrect ones, neither too strict nor too lenient


• Iterate on tasks and tests based on QA feedback - review agent solutions, analyze failures, and refine until the evaluation is fair and robust

What this is not

• Not data labeling


• Not prompt engineering


• Not writing code from scratch - the agent writes most of the code; you guide and evaluate

What we look for

• 5+ years in software development


• Core stack: Python (FastAPI), JavaScript/TypeScript (React), Docker, Postgres, Kafka, Redis


• Experience writing tests (functional, integration)


• English proficiency - B2+

Why this is hard

Frontier models are already good at coding. Creating a task that genuinely challenges the best models is non-trivial. You need to deeply understand where models fail and what scenarios reveal the difference between a good and a bad solution. Tasks have many valid solutions - writing tests that accept all correct solutions and reject incorrect ones is harder than it sounds.

Effort estimate

Tasks for this project are estimated to take 20 hours to complete, depending on complexity. This is an estimate and not a schedule requirement; you choose when and how to work. Tasks must be submitted by the deadline and meet the listed acceptance criteria to be accepted.

Compensation

Up to $50/hr equivalent, depending on level and pace. Tasks are estimated at approximately 20 hours each; you set your own schedule.