AI Safety Expert - Red Team
In short AI
Remote contract for red teaming conversational AI models (jailbreaks, prompt injections, multi-turn manipulation), independent and asynchronous work. Requires native fluency in English and European Portuguese (excluding Brazilian). Pay between 29 and 45 USD per hour.
Description
- Role
- Red team conversational AI models and agents: test jailbreaks, prompt injections, misuse cases, bias exploitation and multi-turn manipulation. Annotate failures, classify vulnerabilities, flag systemic risks, document reproducibly and produce reports, datasets and attack cases. Independent, asynchronous work; optional participation in higher-sensitivity projects with clear guidelines and wellness resources.
- Requirements
- Native fluency in English and European Portuguese (excluding Brazilian Portuguese)
- Prior red teaming experience in adversarial AI, cybersecurity or socio-technical probing
- Strong communication skills to explain risks to technical and non-technical stakeholders
- Preferred
- adversarial ML (jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction), penetration testing, exploit development, reverse engineering, abuse and disinformation analysis, creative skills in psychology, acting or writing
- Conditions
- Contract: independent (service provision)
- Salary: 29 to 45 USD per hour
- Hours: not stated
- Location: remote
- Benefits
- Wellness resources for higher-sensitivity projects
About the job
Mercor connects elite creative and technical talent with leading AI research labs. Headquartered in San Francisco, our investors include Benchmark, General Catalyst, Peter Thiel, Adam D'Angelo, Larry Summers, and Jack Dorsey.
Position: AI Safety Experts — English & Portuguese (global)
Type:Contract
Compensation:$29–$45/hour
Location:Remote
Role Responsibilities
- Red team conversational AI models and agents. Focus on jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation.
- Generate high-quality human data. Annotate failures, classify vulnerabilities, and flag systemic risks.
- Apply structure using taxonomies, benchmarks, and playbooks to maintain consistent testing.
- Document reproducibly. Produce reports, datasets, and attack cases that customers can act on.
- Work independently and asynchronously. Participate in optional higher-sensitivity projects with clear guidelines and wellness resources.
Qualifications
Must-Have
- Native fluency in English and Portuguese (global, excluding Brazilian Portuguese).
- 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.
- Cybersecurity skills: penetration testing, exploit development, reverse engineering.
- Socio-technical risk expertise: harassment/disinfo probing, abuse analysis, conversational AI testing.
- Creative probing skills in psychology, acting, or writing for unconventional adversarial thinking.
Application Process (Takes 20–30 mins to complete)
- Upload resume
- AI interview based on your resume
- Submit form
Resources & Support
- For details about the interview process and platform information, please check:
- For any help or support, reach out to:
PS: Our team reviews applications daily. Please complete your AI interview and application steps to be considered for this opportunity.
Originally posted on Himalayas
How to apply
Upload resume, complete an AI interview based on your resume (about 20 to 30 minutes) and submit the form. Applications are reviewed daily. AI
Prepare your application
A cover letter and a short pitch for this job, written from your profile, and what to learn next.
Sign in and create your profile from your CV. It is private: we share it with no one.
Something wrong or unlawful in this ad? Report it
Similar jobs
Salary compared ⓘ
13 jobs · Cybersecurity and network specialists · remote
see the best paid →Training for this job
- Pós-Graduação Online em Proteção de Dados, IA & CibersegurançaUniversidade Europeiaonline · 35 weeks · starts 05/2027Asked for in this ad: AI / machine learning
- AI in CybersecurityRumosblended · 7 h · 370 €Asked for in this ad: AI / machine learning
- AI+ Security Practitioner™Galileuself-paced · flexible hours · 40 h · 695 € + IVAAsked for in this ad: AI / machine learning
Languages AI
Published on (1)
- Himalayas seen 16 Nov
First seen on 16 Nov, 23:25