> Markdown version of [/jobs/ext/3022870-adversarial-ai-specialist-fully-remote](https://www.wearedevelopers.com/jobs/ext/3022870-adversarial-ai-specialist-fully-remote). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Adversarial AI Specialist - Fully Remote

- **Company:** Mercor, Inc.
- **Location:** New York, NY, United States (Remote available)
- **Experience:** Starter
- **Salary:** $41,600.0 - $45,760.0
- **Contract:** Permanent contract
- **Skills:** Artificial Intelligence, Software System Penetration Testing, Cyber Security, Red Team (Cyber Security), Reverse Engineering
- **Published:** September 21, 2026
- **Apply:** https://www.careerjet.com/jobad/us77215a9558b456e2e0142a028e3913b4

## About the Role

Must-Have

 * Native fluency in English and Urdu.
 * Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing.
 * Strong communication skills to explain risks to technical and non-technical stakeholders.

Preferred

 * Experience in Adversarial ML: jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction.
 * Background in Cybersecurity: penetration testing, exploit development, reverse engineering.
 * Expertise in socio-technical risk: harassment/disinfo probing, abuse analysis, conversational AI testing.
 * Creative probing skills in psychology, acting, or writing for unconventional adversarial thinking.

## Description

* Red team conversational AI models and agents. Conduct jailbreaks, prompt injections, misuse cases, and bias exploitation.
 * Generate high-quality human data. Annotate failures, classify vulnerabilities, and flag systemic risks.
 * Apply structure using taxonomies, benchmarks, and playbooks to maintain testing consistency.
 * Document reproducibly. Produce reports, datasets, and attack cases that customers can act on.
 * Work independently and asynchronously to meet deadlines while improving AI model performance., PS: Our team reviews applications daily. Please complete your AI interview and application steps to be considered for this opportunity.


## Related Videos

- [Hacking AI - how attackers impose their will on AI](https://www.wearedevelopers.com/videos/824-hacking-ai-how-attackers-impose-their-will-on-ai)
- [Thinking Differently - How to Make Money from Cyber Attacks & Cheats](https://www.wearedevelopers.com/videos/745-thinking-differently-how-to-make-money-from-cyber-attacks-cheats)
- [Hacking iOS and Developing for Airbnb with Nicolas Haunold, Software Engineer at Airbnb](https://www.wearedevelopers.com/videos/100361-hacking-ios-and-developing-for-airbnb-with-nicolas-haunold-software-engineer-at-airbnb)
- [Edit Your Future: Queerverse Radical AI](https://www.wearedevelopers.com/videos/909-edit-your-future-queerverse-radical-ai)
- [Hiring AI Native Talents](https://www.wearedevelopers.com/videos/100268-hiring-ai-native-talents)
- [Cyber Security: Small, and Large!](https://www.wearedevelopers.com/videos/259-cyber-security-small-and-large)

## Related Articles

- [Dev Digest 134 - Where pixels sing?](https://www.wearedevelopers.com/magazine/477-dev-digest-134-where-pixels-sing)
- [Dev Digest 121 - AI goes offline](https://www.wearedevelopers.com/magazine/456-dev-digest-121-ai-goes-offline)
- [How to start an AI project for a good cause and boost your career](https://www.wearedevelopers.com/magazine/15-how-to-start-an-ai-project-for-a-good-cause-and-boost-your-career)
- [Dev Digest 137 - AI'm not sure about this](https://www.wearedevelopers.com/magazine/485-dev-digest-137-ai-m-not-sure-about-this)
- [Fully Remote Software Engineer Jobs](https://www.wearedevelopers.com/magazine/447-fully-remote-software-engineer-jobs)
- [Prompt Engineering is a Job of the Past](https://www.wearedevelopers.com/magazine/342-prompt-engineering-is-a-job-of-the-past)