Intelligence professionals evaluate how large language models could be misused to support real-world national security threats, applying defense, cyber operations, counterintelligence, counterterrorism, and related expertise to AI safety research.
Role OverviewThis high-impact, part-time remote engagement is designed for professionals who want to apply government or military experience to anticipating AI-era security risks.
Key Responsibilities- Simulate and assess how malicious actors could use LLMs to plan or enhance violence, terrorism, targeted assassinations, special operations, and tactical attacks.
- Participate in red-team exercises involving jailbreaking attempts and LLM-generated responses.
- Interpret model outputs and determine whether they represent credible, material threats in real-world contexts.
- Professional background in intelligence, defense, cyber operations, counterintelligence, counterterrorism, or a related field.
- Ability to apply government or military experience to evaluating national security risks.
- Remote, part-time engagement.
Up to $200/hr (depending on the project)
Intelligence Expert for AI Red Teaming in McKees Rocks at Unknown Company
This position is listed as part time and able to be worked remotely.