AI Jailbreak & Prompt-Injection Security Expert
The contractor designs and runs evaluations probing AI systems for jailbreak and prompt injection weaknesses, then builds regression test suites. Candidates need 2+ years in adversarial machine learning, LLM red teaming, or AI safety evaluation.
- Ethical Jailbreaks
- LLM Red Teaming
- Prompt Injection
- +1
Posted 6 days ago$50 to $90/h
