Adversarial Prompt Expert.

Adversarial Prompt Expert is a remote red-team track for stress-testing AI systems against adversarial prompts. Reviewers craft attack scenarios, document the failure mode, and pair each successful jailbreak with the rubric clause it violated so the safety team can patch the gap.

Adversarial evaluation is how AuraOne hardens AI models before they ship to customers. Reviewers think like attackers and write up failures with enough rigor that the modeling team can reproduce, fix, and regress-test them.

Review model outputs, label edge cases, and improve training quality across high-volume AI workflows.

• ↳Design adversarial prompts that probe known weakness classes (jailbreak, policy bypass, prompt injection) for Adversarial Prompt Expert assignments.
• ↳Document every successful attack with reproduction steps and the policy clause it violated.
• ↳Score model defenses across single-turn and multi-turn conversations.
• ↳Triage emerging attack vectors and route them to the safety team with severity ratings.
• ↳Maintain a personal library of attack patterns and propose new red-team rubrics.
• ↳Calibrate against the broader red-team cohort to keep coverage and severity consistent.

• ↳Demonstrated experience red-teaming AI systems, security research, or adversarial ML work for Adversarial Prompt Expert work.
• ↳Strong written communication — your reports become the patch ticket.
• ↳Comfort working in policy-grey areas with clear documentation of what was attempted and why.
• ↳Familiarity with prompt-injection, jailbreak, and policy-bypass taxonomies.
• ↳Reliable async availability for at least 10 hours per week.

Fellowship · Feb 11 – Dec 30

Expected schedule: part-time, remote specialist work with program-defined task volume and review pacing.

• Adversarial prompting
• Red-team analysis
• Policy taxonomy
• Failure documentation
• Adversarial prompt testing
• AI model evaluation
• Analytical thinkingLLM experience
• Data annotation
• Literacy
• Presentation developmentAI

AuraOne uses a shared specialist intake to confirm track fit, review readiness, and the best queue for your profile. Applications submitted from partner job boards carry the source, role, and category on the apply URL.