Skip to main content

AI Coding Agent Evaluation Task Developer at toloka-ai

Language

Compensation

$50/hr

Setup
Remote - Sweden
Type
Part-time, Contract, Other
Level
senior
Posted

Description

Mindrift is seeking a freelance, part-time, remote specialist to create and evaluate challenging software-development tasks for a dataset used to assess AI coding agents. The role involves building realistic simulated developer environments, designing task prompts and success criteria, writing functional and integration tests, reviewing agent solutions, and refining tasks based on QA feedback. Candidates should have substantial software-development experience, strong Python/FastAPI and JavaScript/TypeScript/React skills, familiarity with Docker, Postgres, Kafka, and Redis, English proficiency at B2 or higher, and a relevant master's degree or a bachelor's degree with five years of experience. Compensation is paid per accepted task, up to the equivalent of $50 per hour.

For job seekers

Ready to find a role that actually fits?

Upload your résumé, start a Job Search Thread, and let Metaintro rank real openings against your experience — then guide you from search to offer.

Match

Compare live roles against your current evidence.

Position

Turn proof projects into role-specific applications.

Improve

Use market feedback to keep the skill plan current.

Return to navigation