AI Safety / Red Team Specialist
A specialist contractor role for the adversarial testing of the platform's AI analyst and the evaluation of its safety posture against the documented failure modes.
Compensation: US$90 to US$175 per hour
About the Role
The safety of the AI analyst is, in our reading, not something one can verify by inspection alone. It requires adversarial testing by someone whose discipline is precisely to find the failure modes a developer would not look for. This role is structured as a contractor engagement, typically project-based evaluation sprints or part-time ongoing engagement.
Responsibilities
- Conduct adversarial testing of the AI analyst chat and the Drusus Daily editorial pipeline.
- Author threat models against the documented standards (NIST AI Risk Management Framework, OWASP LLM Top 10).
- Identify and document the failure modes the platform is exposed to, and recommend the structural mitigations.
- Advise on the safety-posture documentation as the platform evolves.
What We Are Looking For
- Substantial demonstrated experience in AI safety, red-team work, or adversarial LLM testing.
- Familiarity with the published literature on language-model safety and the standard failure modes (hallucination, prompt injection, regulatory drift).
- Strong written communication; capable of producing the structured reports the engagement requires.
- Capability to operate with the operational discipline that adversarial work in a financial context requires.
How to Apply
Please write to careers@gravenos.com quoting the reference code GRV-020 in the subject line. Include a brief covering note, a CV or comparable record of your work, and any work samples you think relevant. We will reply.