Senior Software Engineer - AI Evaluation Task Designer

Mindrift; Poland; Remote; PLN 146,553 - 209,361; Full time

Job summary

Mindrift is building a dataset to evaluate AI coding agents by creating challenging tasks and evaluation criteria within realistic simulated environments. You will design prompts, define what counts as solved, and ensure tests accommodate multiple valid approaches while remaining robust.

This role requires 5+ years in software development, strong Python (FastAPI) and JS/TS (React) skills, Docker, Postgres, Kafka and Redis experience, plus experience writing functional and integration tests and

Qualifications

• 5+ years of software development experience required.
• Strong experience with Python (FastAPI) and JavaScript/TypeScript (React).
• Experience writing functional and integration tests.
• English proficiency at least B2+. Keep CV in English.

Responsibilities

• Build realistic developer environments and a believable development history.
• Design tasks from intermediate states of environments and define success criteria.
• Write tests that accept multiple valid solutions while rejecting incorrect ones.
• Iterate on tasks and tests based on QA feedback to ensure fairness and robustness.

Skills

5+ years in software development

Python (FastAPI)

JavaScript/TypeScript (React)

Testing (functional, integration)

Tools

Docker

PostgreSQL

Kafka

Redis

Job description

Mindrift is building a dataset to evaluate AI coding agents by creating challenging tasks and evaluation criteria within realistic simulated environments. You will design prompts, define what counts as solved, and ensure tests accommodate multiple valid approaches while remaining robust.

This role requires 5+ years in software development, strong Python (FastAPI) and JS/TS (React) skills, Docker, Postgres, Kafka and Redis experience, plus experience writing functional and integration tests and