Responsibilities
- Design and integrate a new feature into an existing sandbox plugin to enable secure execution of model-generated code during evaluation workflows.
- Enable support for a new category of open-weights artificial intelligence models on the model hosting infrastructure.
- Work alongside researchers to architect and build specialized systems for a novel research initiative.
- Engage with external contributors to advance functionality within the open-source framework or its ecosystem of plugins.
- Troubleshoot and resolve compatibility problems in evaluation tools arising from updates to a lab's latest software development kit.
