You will help evaluate large language models from a cybersecurity perspective. The work combines prompt writing with careful review of model responses, using your experience in security engineering or offensive security.
Assignments are remote and asynchronous. Project scope may vary as cybersecurity evaluation activities become available.
- Write prompts that test cybersecurity knowledge across relevant security scenarios.
- Evaluate model responses for quality, accuracy, and fit for the security topic.
- Use practical security judgment when reviewing AI-generated content.
- Work independently in an asynchronous remote workflow.