Handshake · Career platform connecting job seekers, employers, and educational institutions
AI Red Teamer (Remote)
United StatesData & AIPosted 2026-10-05
Where you can live
Open to people living in United States.
Listed location: Remote (USA)
Taken from the location the company listed. Confirm in the posting before you apply.
What the job is
Writes adversarial prompts and multi-turn scenarios to break AI model safety guardrails, then scores and documents the harmful or incorrect outputs.
What they ask for
- Hands-on experience using multiple LLMs such as ChatGPT, Claude, or Gemini
- Intuition for crafting adversarial prompts
- Clear written communication for documenting experiments
- Strong ethical judgment separating adversarial thinking from personal values
- Ability to engage with harmful content regularly and professionally
Nice to have
- Python or other scripting languages
- Experience with LLM APIs or evaluation tooling
- Prior trust and safety, content moderation, QA, or security research
This is a summary written by software from the company's posting. The posting is the source.
More remote jobs at Handshake