We are building LLM evaluation and training datasets to train LLMs to work on realistic software engineering problems. One of our approaches is to build verifiable SWE tasks based on public repository histories in a synthetic manner with human-in-the-loop, expanding dataset coverage across different programming languages, difficulty levels, and more.
About the Role :
We are seeking experienced software engineers (tech lead level) familiar with high-quality public GitHub repositories to contribute to this project. Candidates should have experience with well-maintained, widely-used repositories with 500+ stars. This role involves hands-on software engineering tasks, including environment automation, issue triaging, and evaluating test coverage and quality.
Why Join Us?
Turing is one of the world’s fastest-growing AI companies, advancing the deployment of powerful AI systems. You will evaluate how LLMs interact with real code, influencing the future of AI-assisted software development. This role offers a unique blend of practical software engineering and AI research.
Daily Responsibilities :
Required Skills :
Note : Experience with repositories having 500+ stars is required.
Nice to Have :
Perks of Freelancing With Turing :
* Le salaire de référence se base sur les salaires cibles des leaders du marché dans leurs secteurs correspondants. Il vise à servir de guide pour aider les membres Premium à évaluer les postes vacants et contribuer aux négociations salariales. Le salaire de référence n’est pas fourni directement par l’entreprise et peut pourrait être beaucoup plus élevé ou plus bas.