AI Evaluation Engineer (Python, QA or Security)

Mindrift; United States; On-site; USD 41,000 - 69,000; Full time

Job summary

Mindrift is building a dataset to evaluate AI coding agents. You will assemble realistic developer environments, including codebases, infrastructure, tickets, docs, and conversations to form a believable development history.

You will design tasks from intermediate states, write tests to verify agent solutions, and iterate on tasks and tests based on QA feedback to ensure fairness and robustness across valid approaches.

Qualifications

• Minimum 5 years in software development.
• Proficiency in English at B2+ level.

Responsibilities

• Build realistic developer environments dataset with codebase, infra, tickets and docs.
• Design tasks from intermediate environment states and define success criteria.
• Write tests to verify agent solutions across valid approaches.
• Iterate on tasks and tests based on QA feedback to achieve fairness and robustness.

Skills

5+ years in software development

English proficiency (B2+)

Tools

Python

FastAPI

JavaScript/TypeScript

React

Docker

Postgres

Kafka

Redis

Job description

What this opportunity involves

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

• 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.

How it works

Compensation

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