Senior Software Engineer (Python) - Agent Evaluation - Freelance/Remote 100+ openings

***This opportunity is intended for experienced Senior Python Engineers only****

Open to candidates in the North America, South America, Asia and Europe.
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 - You must meet all the requirements in order to be considered for this project:

• 5+ years of professional experience with Python.
• Strong experience with FastAPI , pytest , and async/await .
• Hands-on experience with Docker , PostgreSQL , and CI/CD pipelines.
• Proven experience writing and maintaining automated tests (not just executing them).
• Full-stack experience with React and TypeScript is a plus.
• English proficiency at B2 level or higher .
• Availability to work 30+ hours per week .

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

Apply → Pass qualification(s) → Join a project → Complete tasks → Get paid

Hiring & Onboarding Process

The process is designed to move quickly and typically includes the following steps:

1. App review and invitation to a virtual project introduction session (approximately 30 minutes)
2. Platform registration and identity verification
3. Technical assessment (approximately 35 minutes)
4. Background check (completed at no cost to candidates)
5. Onboarding and project-specific training tasks
6. Begin production work!

Additional Requirements

• Willingness to complete identity verification as part of the onboarding process.
• Ability to complete a technical assessment.
• Willingness to join and participate in Discord, which will be used for project communication and updates.
• Successful completion of a background check is required prior to onboarding.
• Reliable internet connection and ability to communicate effectively in a remote environment.