The Role Stress-test large language models by crafting adversarial prompts and multi-turn scenarios that expose safety, bias, hallucination, prompt injection, and guardrail vulnerabilities. Evaluate model responses using harm taxonomies and severity rubrics, document findings, refine testing methods, and collaborate with engineers, data scientists, and researchers to improve AI safety and robustness. The role involves regular exposure to disturbing harmful content. Summary Generated by Built In 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

TCWGlobal Hours:

40 hours per week About the Role As 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 Warning This 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 AI Handshake 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. Read Full Description Skills Required Hands-on experience using multiple large language models, such as ChatGPT, Claude, Gemini, or open-source models Ability to craft adversarial prompts and familiarity with jailbreak or evasion techniques Creative and adversarial problem-solving skills Clear and thoughtful written communication Strong ethical judgment Ability to work independently and collaboratively in feedback-heavy environments Curiosity, persistence, and comfort with experimentation and failure Familiarity with Python or other scripting languages Experience with LLM APIs or evaluation tooling Experience with structured data annotation and rubric-based scoring Prior experience in trust and safety, content moderation, quality assurance, or security research Subject matter expertise in a high-risk domain such as cybersecurity, chemistry, biology, medicine, law, or finance Ability to professionally and sustainably engage with harmful content Handshake Compensation & Benefits Highlights The following summarizes recurring compensation and benefits themes identified from responses generated by popular LLMs to common candidate questions about Handshake and has not been reviewed or approved by Handshake. About This Summary Leave & Time Off Breadth — Time-off practices include flexible/unlimited PTO, companywide recharge weeks in summer and winter, plus additional volunteer and personal holiday time. Feedback suggests sabbaticals and coordinated breaks help people actually use rest time. Parental & Family Support — Parental leave is described as extended for primary and secondary caregivers, and family-oriented policies are highlighted. Fertility and family-support resources are referenced in public materials. Healthcare Strength — Core coverage spans medical, dental, and vision, with added mental-health resources and wellness programming. Feedback suggests these supports contribute meaningfully to overall wellbeing. Learn more about Handshake's Compensation & Benefits → Handshake Insights What's It Like to Work at Handshake? Handshake Culture & Values Handshake Career Growth & Development What's the Work-Life Balance Like at Handshake? Handshake Leadership & Management Handshake Company Growth, Stability & Outlook View all jobs at Handshake View Handshake Profile Report Job