Senior Python Engineer - AI Testing Project (Freelance, Mindrift)
Mindrift offers remote, project-based freelance opportunities for experienced developers to test, evaluate, and enhance AI systems for top tech companies. Participants contribute 20-30 hours per week, focusing on functional testing, code coverage, and environment setup using Python, Docker, and LLMs like Roo Code and Claude. Compensation is task-based, with top performers earning up to $40/hour, plus flexibility and access to a global community.
Applicants need 5+ years in software engineering (primarily Python), advanced pytest and Docker skills, strong Linux/Bash experience, and proficiency with modern Python tools (uv, pyproject.toml). Familiarity with agent evaluation platforms, reading code in C/C++/Rust/Go, and leveraging LLMs for development is essential. English B2 or higher is required.
Freelancers enjoy a supportive, innovative environment with insight into cutting-edge AI projects. Compensation and project allocation are tailored to expertise, performance, and project needs. Please submit your CV in English, indicating your level of English proficiency.
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.
About the Role
This project is suited for a Senior Python developer with deep functional testing experience, strong Linux and Docker skills, the ability to read code across multiple languages with the support of LLMs (e.g., C, Rust, Go) and translate requirements for migration tasks, and confidence using tools like Roo Code or Claude Code to accelerate iterative development.
Key Responsibilities
- Create functional black box tests for large codebases in various source languages
- Create and manage Docker environments to ensure 100% reproducible builds and test execution across different platforms
- Monitor code coverage and configure automated scoring criteria to meet industry benchmark-level standards
- Leverage LLMs (Roo Code, Claude) to accelerate development cycles, automate repetitive tasks, and improve overall code quality
- 5+ years of experience as a Software Engineer (primarily Python)
- Deep experience with pytest (fixtures, session-scoped, timeouts) and designing black-box functional tests for CLI tools
- Expert-level Docker skills (reproducible Dockerfiles, user contexts, secure workspaces)
- Strong Linux & Bash scripting skills and comfort debugging inside containers
- Proficiency with modern Python tooling (uv, pyproject.toml, packaging)
- Ability to read and understand with LLM many coding languages (for example C, C++, Rust, or Go)
- Experience using LLMs (Claude Code, Roo Code, Cursor) to accelerate iterative development and test-case generation
- English language - B2 or higher
Requirements +
- Prior experience with agent evaluation platforms and MCP CLI
Tools and Technologies: Python (pytest, uv, Pillow), Docker, Bash, Git Submodules, C/C++/Rust/Go (reading), Dagger, GitHub Codespaces, LLMs (Claude Code, Roo Code, Cursor), coverage.py, gcov, kcov.
What we can offer
- Freelance project-based collaboration via the Mindrift platform (powered by Toloka AI)
- Fully remote and flexible participation — choose when and how much to contribute (20-30 hours per week)
- Task-based compensation, equivalent to up to $40/hour* depending on performance and volume
- Opportunity to contribute to innovative AI projects for leading tech companies
- Supportive global community
*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.
Similar Jobs
