Remote Offensive Security & Adversarial ML Researcher

AuraOne, Inc.; United States; Remote; USD 276,000 - 344,000; Full time

Job summary

AuraOne, Inc. is seeking a Cybersecurity Research Expert - Offensive Security & Vulnerability Research for a remote US contractor role. You will craft adversarial prompts to test AI systems and document failures with rigor to enable patching.

Reviewers think like attackers, reproduce issues, and assign severity. The role involves collaboration with safety teams to harden models before deployment and requires strong written communication and async availability.

Qualifications

• Demonstrated experience red-teaming AI systems, security research, or adversarial ML 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.

Responsibilities

• Design adversarial prompts that probe known weakness classes (jailbreak, policy bypass, prompt injection).
• 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.

Skills

Adversarial prompting

Red-team analysis

Policy taxonomy

Failure documentation

Cybersecurity research

Job description

AuraOne, Inc. is seeking a Cybersecurity Research Expert - Offensive Security & Vulnerability Research for a remote US contractor role. You will craft adversarial prompts to test AI systems and document failures with rigor to enable patching.

Reviewers think like attackers, reproduce issues, and assign severity. The role involves collaboration with safety teams to harden models before deployment and requires strong written communication and async availability.