LLM Jailbreak Red Teamer

Description

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 & requirements

Adversarial prompt craftingHarm taxonomy classificationMulti-turn attack strategiesStructured vulnerability documentationPolicy violation severity ratingJailbreak technique knowledgeApply Now

Frequently asked questions

Does this role involve producing actually harmful content, or just testing for it?What harm categories will I be working across?Is this full-time or can I work on a per-session basis?// QUICK INFO

Type

Contractor

Compensation

$55–100/hr

Location

Remote

Category

Red Teaming

Posted

July 20, 2026

Apply Now Back to all positions

// RELATED POSITIONS

More Red Teaming rolesRed TeamingSafety Evaluation Analyst$65–75/hrViewRed TeamingAI Safety Red Teamer$65–85/hrViewRed TeamingPrompt Attack Researcher$35–50/hrViewRed TeamingAI Safety Red Teamer — Part Time$35–45/hrViewView all open positions

// READY TO GET STARTED?

Apply in minutes

Create your profile, select your areas of expertise, and start working on frontier AI projects.

Apply Now