AI Red Team Pro: LLM Safety & Adversarial Testing

handshake

United States

Remote

USD 83,000 - 165,000

Full time

14 days+

A complete application in a minute

Tailored resume and cover letter, ready to send.

Get past ATS filters

Job summary

Handshake AI is seeking an AI Red Teamer to stress-test large language models by crafting creative prompts that reveal vulnerabilities in safety filters and guardrails. You will work on models across text, image, and audio capabilities and help advance AI safety for leading research labs.

This contract role requires curiosity, ethical judgment, and the ability to document experiments clearly, including what you tried and what you learned.

Qualifications

  • Design adversarial prompts and evaluate guardrails and safety filters.
  • Ability to responsibly handle harmful content during testing.
  • Experience with multiple LLMs including proprietary and open-source models.

Responsibilities

  • Craft prompts and multi-turn scenarios to stress-test AI guardrails across risk categories.
  • Discover jailbreak, evasion, and prompt-injection techniques.
  • Explore edge cases to provoke disallowed outputs and document results clearly.
  • Evaluate model responses against harm taxonomies and severity rubrics.
  • Document experiments: what you tried, why, and what it revealed.
  • Review and refine adversarial prompts from teammates and contribute to taxonomy development.
  • Collaborate with engineers, data scientists, and researchers to strengthen defenses.
  • Work with potentially disturbing content and stay updated on jailbreaks and model behaviors.

Skills

LLM Red Teaming
Adversarial Prompting
Ethical Judgment
Written Communication
Collaboration

Tools

Python

Job description

Handshake AI is seeking an AI Red Teamer to stress-test large language models by crafting creative prompts that reveal vulnerabilities in safety filters and guardrails. You will work on models across text, image, and audio capabilities and help advance AI safety for leading research labs.

This contract role requires curiosity, ethical judgment, and the ability to document experiments clearly, including what you tried and what you learned.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Remote AI Red Teamer: Stress-Test & Safeguard LLMs
Remote AI Red Teamer: Stress-Test & Safeguard LLMs

Gomyneed Private Limited • United States

Remote
USD 44,000 - 131,000
Remote AI Red Teamer: Stress-Test & Harden LLM Safety
Remote AI Red Teamer: Stress-Test & Harden LLM Safety

Handshake • United States

Remote
USD 83,000 - 152,000
Remote AI Red Teamer: LLM Safety & Adversarial Testing
Remote AI Red Teamer: LLM Safety & Adversarial Testing

Handshake AI • United States

Remote
USD 55,000 - 110,000
AI Red Teamer — LLM Safety & Adversarial Testing
AI Red Teamer — LLM Safety & Adversarial Testing

We Love AI Jobs • United States

Remote
USD 67,000 - 198,000
AI Red Teamer: Adversarial Prompts & Model Safety
AI Red Teamer: Adversarial Prompts & Model Safety

We Love AI Jobs • Seattle (WA)

Hybrid
USD 67,000 - 198,000
AI Red Teamer (LLM Generalist) - Remote
AI Red Teamer (LLM Generalist) - Remote

handshake • United States

Remote
USD 83,000 - 165,000
AI Safety Red Teamer — Adversarial Prompt Hunter
AI Safety Red Teamer — Adversarial Prompt Hunter

Auraone • United States

Remote
USD 96,000 - 116,000
AI Red Teamer (Remote)
AI Red Teamer (Remote)

Handshake AI • United States

Remote
USD 55,000 - 110,000
AI Red Teamer: Offensive Security & Threat Modeling
AI Red Teamer: Offensive Security & Threat Modeling

Handshake • United States

Remote
USD 140,000 - 210,000
Health Insurance
401k match
Parental leave
+1
AI Safety Red Team Expert: Behavioral Health & Model Eval
AI Safety Red Team Expert: Behavioral Health & Model Eval

Auraone • United States

Remote
USD 62,000 - 96,000