LLM Jailbreak Red Teamer
Claru • Remote
Education
Not stated
Type
Hourly
Pay Rate
$55–$100/hr
Listed
13d ago
About this role
From the Claru listing
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.
Requirements
- Must be eligible to work in Remote
- Fluent proficiency in English (Written & Verbal)
- Reliable high-speed internet connection
- Bachelor's degree or equivalent professional experience
- Demonstrated expertise in Generalist
Why this role
Being remote means this LLM Jailbreak Red Teamer position pays $55–$100/hr regardless of your zip code, opening up Generalist work that used to require living in one of a handful of cities.
Skills and categories
Explore other opportunities in related specializations:
Related jobs
Browse All Jobs from Claru
Discover more opportunities on Claru that match your skills and interests.
View All Claru Jobs →Verified Reviews
Community Reviews
Share your experience with Claru
Help other candidates make better decisions by leaving a review.
Sign in to leave a reviewLeave your review
Common questions
What makes this one of Claru's higher-paying roles?
Claru bands its desk-based work by how much judgement a task needs. This listing sits in the top band at $55-$100/hr, alongside its RLHF evaluation, medical and 3D vision annotation and red-teaming roles, all of which expect graduate-level or professional depth in the subject and the ability to justify a score in writing. Its entry-tier text labeling sits at $20-$35/hr for comparison.
Is Claru desk work a steady queue or does it arrive in batches?
Batches. Claru describes this work as asynchronous with no scheduled hours and no meetings: you claim a batch, complete it and submit. There is no guarantee a new batch is waiting when you finish one, so treat it as recurring project income rather than a fixed weekly wage.
How does Claru measure quality on this kind of work?
Through agreement scoring and review. Its evaluation roles set a target for how closely your scores track other annotators, and disagreements with reviewers are resolved in an async comment thread you are expected to answer within a day. Consistently strong scores are what unlock the senior and lead tracks Claru mentions in its listings.
Can I work on Claru from outside the United States?
For the desk-based annotation and evaluation roles, yes: they are listed as remote with no country gate. The country restrictions on Claru apply to its video capture listings, which are limited to the specific markets named on each one.
What does task-based AI training work look like?
Practical, hands-on data work: recording short videos, categorizing images, rating text responses, or analyzing data. Tasks are designed to be short and distinct, typically 5 to 60 minutes each.
What does asynchronous AI training work mean in practice?
No set hours, no check-ins, no meetings. You log in when you want, pick up an available task, complete it, and submit; nobody is waiting on you in real time. That's different from remote employment, where you're expected online during business hours. The tradeoff: you're competing with others for available tasks, so an empty queue means there's simply nothing to do until more work is released.
What does Generalist work look like for a LLM Jailbreak Red Teamer?
Tasks here are scoped to Generalist, not generic labeling. As a LLM Jailbreak Red Teamer, expect to draw on real domain judgment (evaluating outputs, correcting errors, or providing expert reasoning specific to Generalist) rather than following a one-size-fits-all rubric. If you don't have hands-on Generalist background, this is likely not the right listing to start with.
What specific skills does this listing call for?
Data Annotation and AI Training are named directly in the listing. If you don't have hands-on experience with these, expect the screening process to test for them directly rather than accepting adjacent experience as a substitute.
How much does this specific role pay?
This listing is posted at $55–$100/hr, an hourly rate. The range reflects experience level and negotiated terms, not a placeholder, so where you land in it depends on your background and the assessment. Pay can change between when we last checked the listing and when you apply, so confirm the current number on the platform's own application page before committing time.
What happens when I click Apply on this listing?
You'll be taken to Claru's external site to complete your application there. This listing links through a referral, but the process is identical to applying directly; the link just routes you correctly. Create an account on their site and follow their onboarding steps.
Who is behind Claru?
Claru is the contributor-facing brand of Reka AI, which collects human data for frontier AI labs across text, vision, video and robotics. Its board splits into regional video capture work and desk-based annotation and evaluation, and the apply link on this page is an affiliate link that does not change your pay or what you are offered.