LLM Jailbreak Red Teamer
Apply NowReferral link · no cost to you
← Back to all jobs
Get new roles the moment they’re postedTelegramDiscord
CL
Claru.aiAI Training & Evaluation

LLM Jailbreak Red Teamer

Remote$55–$100 per hourContract / Freelance

About the Role

You'll systematically probe large language models to find inputs that cause them to bypass safety guidelines and produce harmful, disallowed, or policy-violating outputs. Your work involves crafting adversarial prompts across defined harm categories — including but not limited to dangerous instructions, deceptive content, and identity manipulation — then documenting exactly what worked, what the model produced, and why the response constitutes a policy violation. You won't be testing randomly; each session is scoped to specific harm categories and model behaviors as directed by the research team. The workflow is structured: you'll receive a target model, a harm taxonomy, and a session goal. You'll then attempt multiple attack vectors per category — direct prompting, role-play framing, multi-turn escalation, encoding tricks, and others — logging each attempt with the full prompt, model response, and a severity rating. Successful jailbreaks get promoted to a verified findings database; failed attempts are still valuable and should be logged with notes on why they failed. Sessions typically run 2–3 hours with a defined scope. The strongest candidates are people who think like adversaries — researchers, security professionals, former CTF competitors, or anyone who has spent time stress-testing systems. You should be methodical enough to document findings reproducibly and creative enough to try non-obvious attack angles. Familiarity with existing jailbreak literature (DAN prompts, prompt injection, etc.) is assumed. You won't be writing exploit code, but you will be thinking in the same mode. Skills: Adversarial prompt crafting, Harm taxonomy classification, Multi-turn attack strategies, Structured vulnerability documentation, Policy violation severity rating, Jailbreak technique knowledge.


Eligibility

Not open to residents of: Afghanistan, Belarus, Central African Republic, Côte d'Ivoire, Cuba, Democratic Republic of the Congo, Ghana, Haiti, Iran, Iraq, Libya, Mali, Myanmar (Burma), Nicaragua, Nigeria, North Korea, Pakistan, Russia, Somalia, South Sudan, Sudan, Syria, Venezuela, Yemen, Zimbabwe, and the regions of Crimea, Donetsk and Luhansk.

Similar Opportunities

Recommended AI training and data annotation positions

View all jobs →
Up to $15per hour
SME CareersFeatured

PowerPoint Specialist

RemoteBangladesh, India & Pakistan onlyContract / FreelanceAdvanced / Expert

1w ago
Up to $51per hour
SME Careers

Senior Video Editor

Remote28 countries onlyContract / FreelanceAdvanced / Expert

3w ago
More AI Training and Evaluation Jobs