Adversarial AI Safety Research Scientist (LLM/Robustness)

AuraOne, Inc.; United States; Remote; USD 138,000 - 165,000; Part time

Benefits offered by this job

Remote work

US-eligible contractor

Job summary

AuraOne, Inc. is seeking a remote LLM Research Scientist (Pre-training & Computer Vision & Adversarial Robustness) to stress-test AI systems against adversarial prompts. You’ll design jailbreaks, document failures with citations, and rate defenses across single- and multi-turn interactions from a red-team perspective.

The contractor role requires strong written reports, policy-vagueness tolerance, and experience with prompt-injection and jailbreak taxonomy. Remote-U.S.-eligible, 10+ hours/week.

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) for LLM Research Scientist (Pre-training & Computer Vision & Adversarial Robustness) 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.

Skills

Adversarial prompting

Red-team analysis

Policy taxonomy

Failure documentation

Adversarial prompt testing

Job description

AuraOne, Inc. is seeking a remote LLM Research Scientist (Pre-training & Computer Vision & Adversarial Robustness) to stress-test AI systems against adversarial prompts. You’ll design jailbreaks, document failures with citations, and rate defenses across single- and multi-turn interactions from a red-team perspective.

The contractor role requires strong written reports, policy-vagueness tolerance, and experience with prompt-injection and jailbreak taxonomy. Remote-U.S.-eligible, 10+ hours/week.