Schedule a call →

<p>Interview fractional leaders this week for <strong>free</strong>!</p>

Join 10,000+ experts earning $15-50/hr training AI models remotely. Flexible freelance work, weekly payments. No AI experience required. Apply in 5 minutes.

Mindrift Icon

Mindrift (mindrift.ai) is the expert-sourcing platform built by Toloka, a Nebius Group (Nasdaq: NBIS) company and a global leader in data services for AI since 2014. Mindrift’s CEO and co-founder, Olga Megorskaya, launched the platform to connect domain experts — from software engineers and physicians to linguists and lawyers — with AI training projects for the world's leading technology companies.Through Mindrift, over 10,000 professionals across 50+ domains and 15+ languages contribute to supervised fine-tuning, reinforcement learning from human feedback (RLHF), model evaluation, and red-teaming for frontier AI models developed by leading global technology companies.Operated by Toloka from Amsterdam, Netherlands, Mindrift offers flexible, fully remote, project-based opportunities — empowering experts to shape the future of generative AI, one task at a time.

Education

Operations

Engineering

Media and Communication

Information Technology

Administrative

Quality Assurance

Sales

Research

Human Resources

Kenya

Nigeria

United States

India

Nairobi County, Kenya

United Kingdom

Lagos State, Nigeria

Philippines

England, United Kingdom

Canada

South Africa

Pakistan

Mindrift is a groundbreaking platform that brings together AI Tutors, revolutionizing the way we interact with artificial intelligence. AI Tutors play a crucial role in shaping the future of AI by crafting texts, evaluating responses, and conducting fact-checks. Through Mindrift.ai, individuals can apply their expertise and writing skills to become the "I" in AI, contributing to the development of AI language models that will benefit industry, society, and science.

The platform offers various roles, from Domain Experts to Writers and Annotators, providing opportunities for professionals to work on diverse projects remotely. AI Tutors have the flexibility to work from anywhere, collaborate with a global team of experts, and get paid based on project complexity. Join Mindrift today to be part of a dynamic community setting the standard for AI innovation under the guidance of experienced team leads. Apply now to make a difference in the world of AI.

Mindrift

Mindrift Logo

### **Description**

_**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**

You’ll create challenging coding test cases that push AI coding systems to their limits:

- Review and refine realistic coding tasks based on provided production codebases with realistic scope, requirements and information sources
- Write comprehensive functional tests that validate actual end-to-end behavior and edge-cases, not just superficial checks
- Craft “fair but hard” challenges where the AI has all the context it needs, but has to work for it (information scattered across files and external sources, complex reasoning required)
- Analyze AI failures to understand what the model struggles with vs. what it masters
- Iterate based on feedback from expert QA reviewers who score your work on 7 quality criteria

**What we look for**

This opportunity is a good fit for experienced developers, software engineers, and/or test automation specialists open to part-time, non-permanent projects. Ideally, contributors will have:

- Degree in Computer Science, Software Engineering or related fields
- 5+ years in software development, primarily Python (pytest, async/await, subprocess, file operations)
- Background in Full-Stack development, with an equal focus on building React-based interfaces and robust Back-end systems
- Experience writing tests (functional, integration – not just running them)
- Docker containers (running evaluations locally in containers)
- CI/CD understanding (GitHub Actions as a user: triggers, labels, reading results)
- English proficiency - B2

**How it works**

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

**Effort estimate**

Tasks for this project are estimated to take 20 hours to complete, depending on complexity. This is an estimate and not a schedule requirement; you choose when and how to work. Tasks must be submitted by the deadline and meet the listed acceptance criteria to be accepted.

**Payment**

- Paid contributions, with rates **up to $80/hour***
- Fixed project rate or individual rates, depending on the project
- Some projects include incentive payments

_
*Note: Rates vary based on expertise, skills assessment, location, project needs, and other factors. Higher rates may be offered to highly specialized experts. Lower rates may apply during onboarding or non-core project phases. Payment details are shared per project._

Freelance Agent Evaluation Engineer | Mindrift - Jobs By Workable

Automate your workflow from idea to production

GitHub Actions

Software Development

Test Automation

Software Development Engineer in Test

Senior Software Engineer

Lead AI Engineer

Enterprise

Tech-Enabled Services

Fractional Agent Evaluation Engineer to create coding test cases for AI systems at tech companies

Fractional Agent Evaluation Engineer

Mindrift

About Mindrift

Growth signals

Headcount change

Team composition

By function

By region

Inside Mindrift

Categories

Markets

Jobs

Past roles

About this page