Senior AI Coding Evaluation Architect

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

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.