AI Red Teamer – LLM Generalist

Handshake

. Stress-test large language models by intentionally trying to break them .

Posted 9/15/2026contractRemote • United StatesMid-LevelSenior💰 $32 - $95 per hourWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in stress-testing large language models and crafting adversarial prompts while ensuring compliance with safety standards. Proficient in evaluating model responses and collaborating with cross-functional teams to enhance AI safety and robustness.

Highest-signal resume keywords

Hands-On Experience With LLMsAdversarial Prompt CraftingFamiliarity With Jailbreak TechniquesExperience With LLM APIsSubject Matter Expertise In Cybersecurity

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Stress-TestingAdversarial Prompt DesignData AnnotationRubric-Based ScoringPython ScriptingEvaluation ToolingContent Safety AssessmentModel EvaluationExperiment DocumentationHarm Taxonomy Development

Soft Skills

Creative Problem-SolvingClear Written CommunicationStrong Ethical JudgmentSelf-Directed CollaborationCuriosity and Persistence

Industry Keywords

Content ModerationTrust and SafetyCybersecurityCBRNInfluence OperationsHigh-Risk Domain ExpertiseRegulatory ComplianceHarmful Material EngagementFeedback-Heavy EnvironmentsEvasion Techniques

Tech Stack

Tools & technologies

Cyber SecurityPython

About the role

Key responsibilities & impact

Stress-test large language models by intentionally trying to break them
Design creative, adversarial prompts exposing unsafe content, bias, broken guardrails, hallucinations, prompt injection weaknesses, and unexpected behaviors
Probe models across content safety, CBRN, cybersecurity, persuasion and influence operations, child safety, self-harm, over-companionship, and regulatory compliance
Test text, image, voice, and agentic model capabilities as project needs require
Craft multi-turn scenarios to stress-test AI guardrails
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, including methods, rationale, and findings
Review and refine adversarial prompts from 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 regularly with potentially disturbing content
Stay current on jailbreaks, attack methods, and evolving model behaviors
Support Handshake AI's work partnering with leading AI research labs to make models safer and more robust

Requirements

What you’ll need

Strong hands-on experience using multiple LLMs, including ChatGPT, Claude, Gemini, and open-source models
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 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
Candidates must be able to engage with harmful material professionally and sustainably
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 a high-risk domain such as cybersecurity, chemistry, biology, medicine, law, or finance
Ability to work remotely from the United States, Monday through Friday, 40 hours per week
Must be authorized to work lawfully in the United States for Handshake
Must not require employment visa sponsorship, as addressed in the application requirements

Benefits

Comp & perks

Support resources are available for exposure to disturbing content
Cash compensation range of $32–$95 per hour
Remote work from the United States
40 hours per week