Remote Self-Harm Safety Red Team Specialist

AuraOne

United States

On-site

USD 82,656 - 123,984

Part time

14 days+
Application generator

Turn this role into an interview — a resume and cover letter built around what this employer wants.

Get past ATS filters

Benefits offered by this job

Remote work
US-eligible

Job summary

AuraOne is seeking a Self-Harm Safety Red Team Specialist for a remote contractor role. You will design adversarial prompts and document failures with precise reproduction steps and policy implications. Your work supports hardening AI systems before deployment.

You will score defenses across turn-based interactions, triage new attack vectors with severity ratings, and expand the red-team rubric library. This is a remote US-eligible contractor position.

Qualifications

  • Experience red-teaming AI systems or adversarial ML work.
  • Strong written communication; reports may become patch tickets.
  • Ability to document attempts and rationale in policy-grey areas.

Responsibilities

  • Design adversarial prompts that probe known weakness classes (jailbreak, policy bypass, prompt injection).
  • Document every successful attack with reproduction steps and the violated policy clause.
  • 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
AI safety
Red-team evaluation
Policy rubrics
Self
Harm
Safety

Job description

AuraOne is seeking a Self-Harm Safety Red Team Specialist for a remote contractor role. You will design adversarial prompts and document failures with precise reproduction steps and policy implications. Your work supports hardening AI systems before deployment.

You will score defenses across turn-based interactions, triage new attack vectors with severity ratings, and expand the red-team rubric library. This is a remote US-eligible contractor position.

Get your free, confidential resume review.
or drag and drop your file here.
Similar jobs

Similar jobs worth comparing

Remote AI Red Team: Adversarial Prompting & Safety
Remote AI Red Team: Adversarial Prompting & Safety

AuraOne • United States

On-site
USD 82,656 - 165,312
"Remote"
Remote Dual-Use AI Red Team Specialist
Remote Dual-Use AI Red Team Specialist

AuraOne • United States

On-site
USD 82,656 - 179,088
Senior Cyber Security PM - Remote Red-Team Lead
Senior Cyber Security PM - Remote Red-Team Lead

AuraOne • United States

On-site
USD 96,432 - 179,088
Remote AI Safety Benchmark Red-Team Specialist MentalHealth
Remote AI Safety Benchmark Red-Team Specialist MentalHealth

AuraOne • United States

On-site
USD 110,000 - 207,000
Remote work
Contractor role
Remote AI Adversarial Red Team Engineer
Remote AI Adversarial Red Team Engineer

AuraOne • United States

On-site
USD 82,656 - 130,872
Remote work (US-eligible)
Contractor terms
Remote AI Policy Adversarial Red Team Specialist
Remote AI Policy Adversarial Red Team Specialist

AuraOne • United States

On-site
USD 82,656 - 165,312
Remote work
Contractor engagement
Remote Elections Integrity AI Red Team Specialist
Remote Elections Integrity AI Red Team Specialist

AuraOne • United States

On-site
USD 82,656 - 165,312
Remote Adversarial AI Risk Evaluator (Red‑Team)
Remote Adversarial AI Risk Evaluator (Red‑Team)

AuraOne • United States

On-site
USD 82,656 - 123,984
Remote AI Safety Red-Teamer: Chemical Toxicology Expert
Remote AI Safety Red-Teamer: Chemical Toxicology Expert

AuraOne • United States

On-site
USD 55,104 - 110,208
Remote AI Safety Red-Team Expert — English & Thai
Remote AI Safety Red-Team Expert — English & Thai

AuraOne • United States

On-site
USD 33,000 - 48,000