Skip to content
aitrainer.work - AI Training Jobs Platform
Software Engineering mercor

AI Red-Teamer — Adversarial AI Testing (Advanced); English & Korean

🇰🇷

Mercor • Remote, South Korea, United States

Education

Not stated

Type

Hourly

Pay Rate

$5–$50/hr

Listed

271d ago

Apply opens Mercor in a new tab.

Apply Now →

About this role

From the Mercor listing

Location: Remote; Geography restricted to USA, South Korea

Type: Full-time or Part-time Contract Work

  • Red team conversational AI models and agents: jailbreaks, prompt injections, misuse cases, bias exploitation, multi-turn manipulation
  • Generate high-quality human data: annotate failures, classify vulnerabilities, and flag systemic risks
  • Apply structure: follow taxonomies, benchmarks, and playbooks to keep testing consistent
  • Document reproducibly: produce reports, datasets, and attack cases customers can act on
  • You bring prior red teaming experience (AI adversarial work, cybersecurity, socio-technical probing)
  • You’re curious and adversarial: you instinctively push systems to breaking points
  • You’re structured: you use frameworks or benchmarks, not just random hacks
  • You’re communicative: you explain risks clearly to technical and non-technical stakeholders
  • You’re adaptable: thrive on moving across projects and customers
  • Adversarial ML: jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction
  • Cybersecurity: penetration testing, exploit development, reverse engineering
  • Socio-technical risk: harassment/disinfo probing, abuse analysis, conversational AI testing
  • Creative probing: psychology, acting, writing for unconventional adversarial thinking
  • You uncover vulnerabilities automated tests miss
  • You deliver reproducible artifacts that strengthen customer AI systems
  • Evaluation coverage expands: more scenarios tested, fewer surprises in production
  • Mercor customers trust the safety of their AI because you’ve already probed it like an adversary
  • Build experience in human data-driven AI red teaming at the frontier of safety
  • Play a direct role in making AI systems more robust, safe, and trustworthy

Requirements

  • Must be eligible to work in one of: Remote, South Korea, United States
  • Fluent proficiency in English (Written & Verbal)
  • Reliable high-speed internet connection

How long hiring takes

Across the AI training platforms we refer candidates to, the median gap between referral and hire is about 30 days. It varies by platform and role, so treat it as a rough guide for this one.

Within 2 weeks
~25%
Within 6 weeks
~60%
Within 3 months
~80%

Talent Pool members

Apply through this link and we can put you forward to Mercor when your profile is a strong match. Not every applicant is submitted. If you're not in the pool yet, set up your profile first.

Set up your profile →

Eligible Languages

Fluent proficiency in English or Korean

English Korean

Why this role

This AI Red-Teamer — Adversarial AI Testing (Advanced); English & Korean role pays $5–$50/hr fully remote, so the Software Engineering work here isn't limited to whoever happens to live near an AI lab's office.

Skills and categories

Explore other opportunities in related specializations:

Related jobs

Mercor

Browse All Jobs from Mercor

Discover more opportunities on Mercor that match your skills and interests.

View All Mercor Jobs →

Verified Reviews

Loading reviews…

Community Reviews

Loading reviews…
💬

Share your experience with Mercor

Help other candidates make better decisions by leaving a review.

Sign in to leave a review

Common questions

Does it cost money to apply to Mercor?

No, applying and joining Mercor is free. Mercor's revenue comes from a fee it charges the client on top of your hourly rate, not from applicants. Treat any request for payment to join as a red flag.

Is Mercor for freelancers or full-time contractors?

Mercor places you with one client for a defined engagement, like 'Python Tutor for 3 months', rather than having you grab small tasks from a shared queue. Most roles function as steady contract work, not one-off gigs.

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 Software Engineering work look like for an AI Red-Teamer — Adversarial AI Testing (Advanced); English & Korean?

Tasks here are scoped to Software Engineering, not generic labeling. As an AI Red-Teamer — Adversarial AI Testing (Advanced); English & Korean, expect to draw on real domain judgment (evaluating outputs, correcting errors, or providing expert reasoning specific to Software Engineering) rather than following a one-size-fits-all rubric. If you don't have hands-on Software Engineering background, this is likely not the right listing to start with.

What specific skills does this listing call for?

English and Korean 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 $5–$50/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.

Do I need to be fluent in English or Korean?

Yes. This role specifically requires English or Korean proficiency, on top of the English most AI training work assumes by default. If English is not a language you're fluent in, this is not the right role. Filter for your native language to find better-matched listings.

What happens when I click Apply on this listing?

You'll be taken to Mercor'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.

Can I apply from outside South Korea or the United States?

This specific role is open only to people based in South Korea and the United States. If you are somewhere else, applying is unlikely to lead to an offer even if you pass the assessment, because the restriction is usually about where the work can legally be contracted rather than your skills. Read the full description for any tax-residency or right-to-work caveats before you apply, since they can differ by country.

How soon will I start working after applying to Mercor?

Not immediately. Mercor is a talent marketplace, not a task queue, so applying puts you in a pool of candidates. You start working only once a specific client, like a major AI lab, selects your profile, and that matching process can take weeks.