About the job
Please submit your CV in English and specify your level of English proficiency.
Mindrift is a dynamic platform that connects specialists with project-based opportunities in artificial intelligence for leading technology companies. Our primary focus is on testing, evaluating, and enhancing AI systems. This position is project-based rather than a permanent role.
About the Role
We are seeking a Senior Python Developer who possesses extensive functional testing expertise, proficient Linux and Docker capabilities, and the ability to analyze and understand code across various programming languages (including C, Rust, and Go), leveraging large language models (LLMs) to facilitate code migration tasks. The ideal candidate will also be comfortable utilizing tools such as Roo Code or Claude Code to streamline development processes.
Key Responsibilities
- Design and implement functional black-box tests for extensive codebases in multiple programming languages.
- Set up and manage Docker environments to guarantee fully reproducible builds and test executions across diverse platforms.
- Track code coverage and establish automated scoring criteria to align with industry-standard benchmarks.
- Utilize LLMs (such as Roo Code and Claude) to expedite development cycles, automate repetitive tasks, and enhance overall code quality.
Requirements
- A minimum of 5 years of experience as a Software Engineer, with a strong focus on Python.
- In-depth experience with pytest (including fixtures, session-scoped tests, timeouts) and crafting black-box functional tests for command-line interface (CLI) tools.
- Proficient in Docker, including crafting reproducible Dockerfiles and ensuring secure workspaces.
- Strong Linux and Bash scripting skills, with the ability to troubleshoot within containers.
- Familiarity with contemporary Python tooling (e.g., uv, pyproject.toml, packaging).
- Capability to read and comprehend multiple coding languages with the aid of LLMs (e.g., C, C++, Rust, or Go).
- Experience with LLMs (Claude Code, Roo Code, Cursor) to enhance iterative development and test-case generation.
- Proficient in English, with a minimum proficiency level of B2.
Preferred Qualifications
- Previous experience with agent evaluation platforms and MCP CLI.
Tools and Technologies: Python (pytest, uv, Pillow), Docker, Bash, Git Submodules, C/C++/Rust/Go (code reading), Dagger, GitHub Codespaces, LLMs (Claude Code, Roo Code, Cursor), coverage.py, gcov, kcov.
Benefits
What We Offer
- Freelance, project-based collaboration through the Mindrift platform (powered by Toloka AI).
- Completely remote and flexible participation—choose your hours and workload (20-30 hours per week).
- Compensation based on tasks, potentially reaching up to $50/hour* based on performance and workload.
- Opportunity to engage in innovative AI projects for top-tier tech organizations.

