About the role
The team works to improve AI safety and model robustness. The AI Red Teamer crafts adversarial prompts to uncover vulnerabilities in large language models. This involves exploring edge cases and discovering ways around safety filters to expose potential harms.
Our summary of the posting; the original is on the Handshake careers page.
What the posting requires
- Required
- LLM
- ChatGPT
- Claude
- Gemini
- Open-source models
- Creative
- Written communication
- Ethical judgment
- Self-directed
- Collaborative
- Preferred
- Adversarial prompts
- Jailbreak
- Python
- LLM APIs
- LLM evaluation tooling
- Structured data annotation
These tags are our reading of the posting. They can miss something; the original posting is the reference.