AI Summary
Join Mercor as a Red Team Specialist to evaluate conversational AI models for vulnerabilities, generate human data, and collaborate with AI research teams to improve model safety and robustness.
Key Highlights
Evaluate conversational AI models for vulnerabilities
Generate high-quality human data
Collaborate with AI research teams
Technical Skills Required
Benefits & Perks
$56/hour
Remote work
Part-time or full-time contract work
Job Description
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: Red Team Specialist
Type: Full-time or Part-time Contract Work
Compensation: $56/hour
Location: Remote
Commitment: 20+ hours/week
Role Responsibilities
- Evaluate conversational AI models for vulnerabilities such as jailbreaks, prompt injections, and bias exploitation.
- Generate high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks.
- Apply structure by following taxonomies, benchmarks, and playbooks to ensure consistent testing.
- Document reproducibly by producing reports, datasets, and attack cases that customers can act on.
- Collaborate with AI research teams to improve model safety and robustness.
Must-Have
- Fluent Language Skills Required: English & German
- Prior experience in red teaming (AI adversarial work, cybersecurity, socio-technical probing).
- Strong communication skills to explain risks clearly to technical and non-technical stakeholders.
- Ability to work independently and adapt across projects and customers.
- Experience in Adversarial ML: jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction.
- Cybersecurity skills: penetration testing, exploit development, reverse engineering.
- Expertise in socio-technical risk: harassment/disinfo probing, abuse analysis, conversational AI testing.
- Creative probing skills: psychology, acting, writing for unconventional adversarial thinking.
- Hourly contractor
- Paid weekly via Stripe Connect
- Upload resume
- AI interview based on your resume
- Submit form
- For details about the interview process and platform information, please check: https://talent.docs.mercor.com/welcome/welcome
- For any help or support, reach out to: support@mercor.com
,