Senior Python Engineer LLM Evaluation US

You will help evaluate and improve software engineering data used to train and benchmark large language models. The work combines hands-on coding judgment with structured reviews of AI-generated solutions.

You will work across Python, C/C++, Rust, Go, Java, and JavaScript, including ReactJS. The role focuses on systems programming, infrastructure, performance-critical applications, scalability, and reliability.

• Curate code examples and create precise solutions for model-training datasets.
• Correct and refine code across Python, C/C++, Rust, Go, Java, and JavaScript, including ReactJS.
• Review AI-generated code for correctness, efficiency, scalability, reliability, and performance.
• Build agents that verify systems-level and infrastructure code.
• Identify recurring error patterns and assess model capabilities across the software engineering lifecycle.
• Design verification methods that can automatically validate solutions to software engineering tasks.

The listing does not provide a pay rate. This is a flexible contractor engagement with an initial one-month duration and possible extensions based on performance and fit.

• Workload: 20 or more hours per week.
• Experience: At least three years of software engineering experience.
• Technical background: Strong systems programming, infrastructure, or backend development experience, especially with Python, C/C++, Rust, or Go.
• Production skills: Experience building and deploying scalable, production-grade software.
• Engineering judgment: Strong knowledge of software architecture, design, development, debugging, and code-quality review.
• Communication: Ability to write and explain clear, structured evaluation rationales.