About the role
The team strengthens AI systems for research organizations. The AI Red Teamer devises creative prompts to expose weaknesses in language models, looking for harmful outputs and unexpected behaviors. This work involves exploring unusual scenarios and recording observations to enhance AI security.
Our summary of the posting; the original is on the Handshake careers page.
What the posting requires
- Required
- LLM
- Adversarial prompts
- ChatGPT
- Claude
- Gemini
- Open-source models
- Creative
- Written communication
- Ethical judgment
- Self-directed
- Preferred
- Jailbreak
- Python
- LLM APIs
- Evaluation tooling
- Data annotation
- Rubric-based scoring
These tags are our reading of the posting. They can miss something; the original posting is the reference.