Remote Adversarial AI Safety Red‑Team Evaluator

AuraOne

United States

On-site

USD 55,104 - 110,208

Part time

14 days+
Application generator

A complete application in a minute — tailored resume and cover letter, ready to send.

Get past ATS filters

Benefits offered by this job

Remote work
Contractor position

Job summary

AuraOne is seeking a Persuasion Risk Risk Evaluator for a remote contractor role focused on adversarial evaluation of AI systems. Reviewers craft attack scenarios and document failures with rigor so the modeling team can reproduce, fix, and regress-test them.

You will design prompts, document reproduction steps, score defenses across turns, and triage new attack vectors with severity ratings. This is a remote contractor role with US eligibility and hourly compensation to be confirmed after

Qualifications

  • Experience red-teaming AI systems, security research, or adversarial ML.
  • Clear written reports; reports become patch tickets.
  • Ability document what was attempted and why in policy-grey areas.
  • Familiar with prompt-injection, jailbreak, and policy-bypass taxonomies.
  • Available remotely for at least 10 hours per week.

Responsibilities

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

Skills

Adversarial prompting
Red-team analysis
Policy taxonomy
Failure documentation
Persuasion Risk Risk evaluation
AI safety
Red-team evaluation
Policy rubrics
Persuasion
Risk

Job description

AuraOne is seeking a Persuasion Risk Risk Evaluator for a remote contractor role focused on adversarial evaluation of AI systems. Reviewers craft attack scenarios and document failures with rigor so the modeling team can reproduce, fix, and regress-test them.

You will design prompts, document reproduction steps, score defenses across turns, and triage new attack vectors with severity ratings. This is a remote contractor role with US eligibility and hourly compensation to be confirmed after

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

Similar jobs worth comparing

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 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 Adversarial Security Researcher
Remote AI Adversarial Security Researcher

AuraOne • United States

On-site
USD 96,000 - 124,000
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 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 Adversarial AI Security Researcher
Remote Adversarial AI Security Researcher

AuraOne • United States

On-site
USD 120,000 - 180,000
Remote Harmful Instruction Risk Evaluator
Remote Harmful Instruction Risk Evaluator

AuraOne • United States

On-site
USD 82,656 - 165,312
Remote AI Adversarial Prompt Red Teamer
Remote AI Adversarial Prompt Red Teamer

AuraOne • United States

On-site
USD 82,656 - 165,312
Vulnerability Researcher, AI Adversarial Testing (Remote)
Vulnerability Researcher, AI Adversarial Testing (Remote)

AuraOne • United States

On-site
USD 83,000 - 165,000
Remote AI Adversarial Prompting Red Teamer
Remote AI Adversarial Prompting Red Teamer

AuraOne • United States

On-site
USD 96,432 - 179,088