Remote AI Red Team Specialist: Adversarial Prompt Testing

AI Trainer Jobs

United States

Remote

USD 90,000 - 96,000

Full time

3 days ago
Be an early applicant
Application generator

Stand out for this role — generate a tailored resume and cover letter in about a minute.

Get past ATS filters

Job summary

AI Trainer Jobs is seeking a Capability Elicitation Red Team Specialist for a remote, US-eligible contractor role focused on stress-testing AI systems against adversarial prompts. You will design investigations, document failures with rubric mappings, and help patch gaps before deployment.

Leverage adversarial evaluation to harden models prior to customer delivery, writing up failures with rigor so the team can reproduce, fix, and regress-test them.

Qualifications

  • Experience red-teaming AI systems, security research, or adversarial ML work.
  • Strong written communication and documentation.
  • Comfort working in policy-grey areas with clear rationale.
  • 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 Capability Elicitation Red Team Specialist 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.

Skills

Adversarial prompting
Red-team analysis
Policy taxonomy
Failure documentation
Adversarial prompt testing
AI safety
Red-team evaluation
Policy rubrics
Capability
Elicitation

Job description

AI Trainer Jobs is seeking a Capability Elicitation Red Team Specialist for a remote, US-eligible contractor role focused on stress-testing AI systems against adversarial prompts. You will design investigations, document failures with rubric mappings, and help patch gaps before deployment.

Leverage adversarial evaluation to harden models prior to customer delivery, writing up failures with rigor so the team can reproduce, fix, and regress-test them.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Remote AI Safety Red Team Specialist (Adversarial Testing)
Remote AI Safety Red Team Specialist (Adversarial Testing)

AI Trainer Jobs • United States

Remote
USD 90,000 - 96,000
Remote AI Adversarial Red Teamer: Jailbreak & Prompt Injection
Remote AI Adversarial Red Teamer: Jailbreak & Prompt Injection

AI Trainer Jobs • United States

Remote
USD 96,000 - 138,000
Remote AI Adversarial Testing Red Team Engineer
Remote AI Adversarial Testing Red Team Engineer

AI Trainer Jobs • United States

Remote
USD 96,000 - 138,000
Remote AI Adversarial Red Teamer – Supply Chain Security
Remote AI Adversarial Red Teamer – Supply Chain Security

AI Trainer Jobs • United States

Remote
USD 96,000 - 138,000
Remote AI Safety Red Team Specialist
Remote AI Safety Red Team Specialist

AI Trainer Jobs • United States

Remote
USD 90,000 - 96,000
Remote AI Red Team - Safety & Adversarial Testing
Remote AI Red Team - Safety & Adversarial Testing

Obsidian • San Francisco (CA)

On-site
USD 100,000 - 140,000
Remote AI Safety Red-Team Risk Evaluator
Remote AI Safety Red-Team Risk Evaluator

AI Trainer Jobs • United States

Remote
USD 90,000 - 96,000
Remote LLM Red Team: Failure Modes & Edge Cases
Remote LLM Red Team: Failure Modes & Edge Cases

AI Trainer Jobs • United States

Remote
USD 83,000 - 124,000
Remote AI Red-Teamer: Adversarial Testing Expert
Remote AI Red-Teamer: Adversarial Testing Expert

Crossing Hurdles • United States

Remote
USD 74,390 - 152,913
Remote AI Safety Red Team Specialist
Remote AI Safety Red Team Specialist

AI Trainer Jobs • United States

Remote
USD 90,000 - 96,000