As an LLM Code Evaluation Software Engineer, you will help create datasets used to train and test large language models. You will work with researchers and other teams to assess AI-generated code and improve the quality of coding solutions.
The role covers several programming languages and includes both hands-on software development and careful written evaluation. You will explain your judgments clearly and help measure what AI systems can do across the software engineering process.
- Curate code examples and create solutions in Python, JavaScript, ReactJS, C, C++, Java, Rust, and Go.
- Review and improve AI-generated code for efficiency, scalability, reliability, and code quality.
- Build verification agents and automated checks that find errors and assess software solutions.
- Study parts of the software engineering cycle and evaluate model performance against industry benchmarks.
- Work with cross-functional teams to improve AI coding solutions.
What it pays and takes
This is a contractor, part-time engagement. The listing does not provide a pay rate. It calls for a flexible commitment lasting one month, with possible extensions based on performance and fit.
- Pay: No rate is provided in the listing.
- Time: Flexible work, with a minimum of 10 hours and up to 40 hours per week; the structured listing also indicates 20+ hours per week.
- Location: You must be based in the United States, Canada, or a listed Western European country, including Austria, Belgium, France, or Germany.
- Language: English is required for clear spoken and written evaluation rationales.
- Experience: At least three years of software engineering experience, despite the listing's entry-level classification.
- Skills: Full-stack application development, production software deployment, architecture, design, development, debugging, and code review.
- Contract terms: Contractor work with no medical or paid leave.
- Helpful background: Experience with LLM evaluation or AI model training is a plus.
How it works
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 that generate and understand content. Engineers and other specialists prepare examples, review model responses, and test whether AI systems follow instructions, solve problems, and produce reliable results. Experienced contributors are paid for applying their professional judgment to these evaluations.
