Mercor is on the lookout for excellent contributors and maintainers to join their exciting journey in open-source projects. This job offers a fantastic opportunity to work with well-known Python repositories, benchmarking coding agents and evaluating their performance. The team values collaboration and flexibility, allowing contributors to work remotely and on their own schedule.
You'll be responsible for
⚙️
Benchmarking performance
Working with clients to benchmark the performance of various coding agents across open-ended software engineering tasks in well-documented Python repositories.🔍
Evaluating coding agents
Evaluating the performance of the coding agent across predefined criteria.💻
Collaborating remotely
Engaging in a fully remote role that allows for flexible scheduling and collaboration with leading AI labs and enterprises.
