Senior Software Engineer, LLM Code Evaluation

Create and improve code examples and solutions for training and benchmarking large language models. Review AI-generated implementations for correctness, performance, scalability, and reliability.

• Curate code examples and write accurate solutions.
• Correct and evaluate code in Python, C/C++, Rust, Go, Java, and JavaScript, including ReactJS.
• Review systems-level code and assess software across architecture, API design, implementation, launch, monitoring, and ongoing maintenance.
• Build automated agents that check infrastructure code quality and identify recurring errors.
• Design ways to automatically verify solutions to software engineering tasks.
• Give clear, structured explanations for technical evaluations.

What the role requires

• Location: Candidates must be based in the United States.
• Language: Fluency in English.
• Time: 20+ hours per week; the schedule is flexible.
• Engagement: Contractor role expected to last one month, with possible extensions based on performance and fit.
• Strong systems programming, infrastructure, or backend development skills, especially in Python, C/C++, Rust, or Go.
• Experience building and deploying scalable, production-grade software.
• Knowledge of software architecture, design, development, debugging, and code review.
• Experience building production systems at a high-scale engineering organization and a strong computer science foundation are helpful. Practical skill is considered alongside formal education.

How to apply

Apply on OpenTrain with your resume, then complete the application on the hiring site.

About AI training work

AI training is the human work behind systems such as large language models: people prepare examples and review model responses so the systems can improve. OpenTrain is a platform where people can find AI training and data-labeling roles, build a profile, and apply.