About the job
We invite you to submit your CV in English, including your proficiency level in the English language.
At Mindrift, we connect talented specialists with project-based opportunities in artificial intelligence, partnering with leading tech companies to test, evaluate, and enhance AI systems. Please note that this is a project-based role and does not offer permanent employment.
Role Overview
This position requires a Senior Python Engineer with extensive experience in functional testing, robust knowledge of Linux and Docker, and the ability to understand and translate requirements across multiple programming languages with the aid of Large Language Models (LLMs) such as C, Rust, and Go. A strong competence in using tools like Roo Code or Claude Code for expedited iterative development is essential.
Primary Responsibilities
- Develop functional black box tests for substantial codebases in diverse programming languages.
- Establish and manage Docker environments to guarantee 100% reproducibility in builds and test execution across various platforms.
- Track code coverage and set automated scoring criteria to align with industry standard benchmarks.
- Utilize LLMs (Roo Code, Claude) to enhance development cycles, automate repetitive tasks, and elevate code quality.
Candidate Requirements
- Minimum of 5 years of experience as a Software Engineer, primarily focusing on Python.
- In-depth experience with pytest (fixtures, session-scoped, timeouts) and crafting black-box functional tests for CLI tools.
- Advanced Docker expertise (creating reproducible Dockerfiles, managing user contexts, ensuring secure workspaces).
- Proficient in Linux and Bash scripting with a strong ability to debug within containers.
- Familiarity with modern Python tools (uv, pyproject.toml, packaging).
- Capability to read and interpret code in various languages (such as C, C++, Rust, or Go) using LLMs.
- Experience with LLMs (Claude Code, Roo Code, Cursor) to facilitate iterative development and generate test cases.
- English proficiency of B2 or higher.
Preferred Qualifications
- Previous experience with agent evaluation platforms and MCP CLI.
Technologies and Tools: 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 Offer
- Freelance project-based collaboration through the Mindrift platform (powered by Toloka AI).
- Completely remote and flexible engagement — you can choose your contribution schedule (20-30 hours per week).
- Compensation based on tasks, with rates up to $30/hour, depending on performance and workload.
- Opportunity to engage in groundbreaking AI projects for top-tier technology companies.

