Remote Python Engineer for AI & LLM Evaluation (Freelance)

Zettamine Labs; United States; Remote; USD 83,000 - 138,000; Full time

Benefits offered by this job

Remote work

Job summary

ZettaMine!!! is seeking a Python Developer for a freelancing project focused on AI research and software engineering. The role involves evaluating and improving LLMs through real-world code analysis, testing, and repository evaluation.

Work is remote with a 2–3 week engagement and a 40-hour week. The candidate should have at least 2+ years of experience, strong Python skills, and familiarity with Git, Docker, and basic CI/CD.

Qualifications

• Minimum 2+ years of overall experience.
• Strong hands-on experience with Python.
• Proficiency in Git, Docker, and basic software pipeline setup.
• Ability to understand, analyze, and navigate complex codebases.
• Comfortable running, modifying, and testing real-world projects locally.
• Familiarity with high-quality public GitHub repositories.
• Strong understanding of software development practices and code quality.
• Experience contributing to or evaluating open-source projects is an added advantage.

Responsibilities

• Analyze and triage GitHub issues across trending open-source libraries.
• Set up and configure code repositories, including Dockerization and development environment setup.
• Evaluate unit test coverage and overall testing quality.
• Modify and execute codebases locally to assess LLM performance in bug-fixing scenarios.
• Identify software bugs, code issues, and potential improvements.
• Collaborate with researchers to identify repositories and issues that challenge LLM capabilities.
• Support AI research initiatives through hands-on software engineering and code evaluation.

Skills

Python

Codebase navigation

Open-source familiarity

LLM evaluation

Tools

Git

Docker

CI/CD basics

Job description

ZettaMine!!! is seeking a Python Developer for a freelancing project focused on AI research and software engineering. The role involves evaluating and improving LLMs through real-world code analysis, testing, and repository evaluation.

Work is remote with a 2–3 week engagement and a 40-hour week. The candidate should have at least 2+ years of experience, strong Python skills, and familiarity with Git, Docker, and basic CI/CD.