AI Red Teamer (Remote)

Gomyneed Private Limited

United States

Remote

USD 44,000 - 131,000

Full time

14 days+

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Job summary

Handshake AI is seeking an AI Red Teamer to stress-test large language models through creative, adversarial prompts and structured evaluation. You will explore guardrails, safety filters, and potential vulnerabilities across content safety and risk domains.

You will document and share findings with engineers and researchers, contributing to taxonomy development and defense strategies while maintaining high ethical standards and professional judgment.

Qualifications

  • Experience with large language models and evaluation.
  • Ability to design adversarial prompts and jailbreak scenarios.
  • Strong written communication and documentation.
  • Ethical judgment and ability to separate adversarial thinking from values.
  • Self-directed with collaborative work style.

Responsibilities

  • Craft prompts and multi-turn scenarios to stress-test guardrails.
  • Identify jailbreaks, evasion techniques, and prompt injections.
  • Document experiments with methods, outcomes and rationale.
  • Rate model outputs using harm taxonomies and clarity rubrics.
  • Collaborate with engineers and researchers to strengthen defenses.

Skills

LLM experience
Adversarial prompting
Creative problem solving
Clear written communication
Ethical judgment
Self-directed
Collaborative
Curiosity

Tools

Python
LLM APIs
Evaluation tooling

Job description

# AI Red Teamer (Remote)Handshake Remote (USA) Full-timeFull-timeRemoteAI & Machine Learning---## About this role**Experience level:** Experienced | **Work mode:** Remote | **Location:** Remote (USA)**California eligibility: We are unable to hire candidates residing in California for this role.**# AI Red Teamer (LLM Generalist)**Location:** Remote (USA)**Employment type:** W-2, hourly, employed through TCWGlobalHours: 40 hours per week## About the RoleAs an AI Red Teamer, you will stress-test large language models by intentionally trying to break them. Rather than checking whether an answer is correct, you will design creative, adversarial prompts that expose vulnerabilities: unsafe content, bias, broken guardrails, hallucinations, prompt injection weaknesses, and unexpected behaviors. Your work directly supports AI safety and model robustness for leading research labs.This is a generalist red teaming role. You will probe models across the full spectrum of risk categories, including content safety, CBRN (chemical, biological, radiological, nuclear), cybersecurity, persuasion and influence operations, child safety, self-harm, over-companionship, and regulatory compliance. Red teaming may span text, image, voice, and agentic model capabilities depending on project needs.This role requires creativity, curiosity, and an ability to think like an adversary while operating with strong ethical judgment.## Day-to-Day Responsibilities* Craft creative prompts and multi-turn scenarios to stress-test AI guardrails across diverse risk categories* Discover ways around safety filters, restrictions, and defenses using jailbreak, evasion, and prompt injection techniques* Explore edge cases to provoke disallowed, harmful, or incorrect outputs* Evaluate and score model responses against structured harm taxonomies and severity rubrics* Document experiments clearly, including what you tried, why you tried it, and what it revealed* Review and refine adversarial prompts generated by other team members* Contribute to harm taxonomy development, calibration exercises, and inter-rater reliability work* Collaborate with engineers, data scientists, and researchers to share findings and strengthen defenses* Work with potentially disturbing content on a regular basis (see Content Warning below)* Stay current on jailbreaks, attack methods, and evolving model behaviors## Desired Capabilities**Core*** Strong hands-on experience using multiple LLMs (ChatGPT, Claude, Gemini, open-source models, etc.)* Intuition for crafting adversarial prompts; familiarity with jailbreak or evasion techniques is a strong plus* Creative, adversarial problem-solving skills* Clear and thoughtful written communication* Strong ethical judgment and the ability to separate adversarial thinking from personal values* Self-directed, collaborative, and comfortable in feedback-heavy environments* Curiosity, persistence, and comfort with frequent failure in experimentation**Nice to Have*** Familiarity with Python or other scripting languages* Experience working with LLM APIs or evaluation tooling* Comfort with structured data annotation and rubric-based scoring* Prior work in trust and safety, content moderation, QA, or security research* Subject matter expertise in any high-risk domain (cybersecurity, chemistry, biology, medicine, law, finance, etc.)## You Will Thrive Here If* You treat every model response as a hypothesis to challenge* You can switch between creative free-association and rigorous documentation in the same session* You go deep into unusual interests (fandoms, niche internet cultures, gaming exploits, Wikipedia rabbit holes, etc.)* You come from a creative background: writing, visual art, improv, puzzle design, or similar* You are energized by finding the thing nobody else thought to try* You are genuinely passionate about AI and follow the space closely## Content WarningThis role involves regular and deliberate exposure to harmful content. You will encounter and intentionally generate content involving violence, self-harm, hate speech, sexually explicit material, child safety scenarios, and other categories of harmful output as part of structured adversarial testing. Candidates must be able to engage with this material professionally and sustainably. Support resources are available.## About Handshake AIHandshake AI partners with leading AI research labs to make models safer and more robust. Our red teaming operations help identify vulnerabilities before they reach users, contributing directly to the responsible development of frontier AI systems.$32 – $95 per hourCompany: HandshakeLocation: Remote (USA)Job Type: Full-timeCategory: AI & Machine LearningWork Mode: RemoteApply Company Site You'll be redirected to the company's site to complete your application.
Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

AI Red Teamer (Remote)
AI Red Teamer (Remote)

Handshake • United States

Remote
USD 83,000 - 152,000
AI Red Teamer (Remote)
AI Red Teamer (Remote)

Handshake AI • United States

Remote
USD 55,000 - 110,000
AI Red Teamer (Remote)
AI Red Teamer (Remote)

We Love AI Jobs • United States

Remote
USD 67,000 - 198,000
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
Strategic Projects Lead, Safety
Strategic Projects Lead, Safety

Handshake • New York (NY)

Hybrid
USD 96,000 - 160,000
Equity
401(k) match
Financial coaching
+9
AI Safety Red Teamer Expert
AI Safety Red Teamer Expert

mercor • United States

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

Handshake • United States

Remote
USD 140,000 - 210,000
Health Insurance
401k match
Parental leave
+1
Behavioral Health Expert, AI Safety and Model Evaluation
Behavioral Health Expert, AI Safety and Model Evaluation

Auraone • United States

Remote
USD 62,000 - 96,000
AI Red Teamer, CBRNE (Remote)
AI Red Teamer, CBRNE (Remote)

Handshake • United States

Remote
USD 140,000 - 210,000
Remote work in the United States
Remote AI Safety & Red Teaming Architect
Remote AI Safety & Red Teaming Architect

Weekday • United States

Remote
USD 69,000 - 124,000