Ai Red Team Specialist - Remote | Up To $22/Hr

Mercor; San Francisco (CA); Hybrid; GBP 17,000 - 23,000; Full time

Job summary

Mercor is seeking AI Safety Experts to test and harden conversational AI models remotely. This contract role focuses on red-teaming, jailbreaks, and vulnerability analysis, with an emphasis on safe, reproducible data generation and clear reporting.

The position requires native-level English and Punjabi, sharp attention to detail, and the ability to work independently with flexible hours. Compensation is $16–$22 per hour, commensurate with experience, and located remotely.

Qualifications

• Fluent in English and Punjabi; native fluency required.
• Strong judgment about language and content.
• Rigorous attention to detail; notice subtle errors and inconsistencies.
• Structured approach; consistently follow guidelines and quality standards.
• Effective communication to explain reasoning to technical and non-technical audiences.
• Adaptability across projects, task types, and customers.

Responsibilities

• Red team conversational AI models and agents. Perform 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. Follow taxonomies, benchmarks, and playbooks to keep testing consistent.
• Document reproducibly. Produce reports, datasets, and attack cases customers can act on.
• Work independently and asynchronously. Ensure flexible hours and meet deadlines.

Skills

English

Punjabi

Attention to detail

Structured approach

Communication

Adaptability

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: AI Safety Experts — English & Punjabi
Type: Contract
Compensation: $16–$22/hour
Location: Remote

Role Responsibilities

• Red team conversational AI models and agents. Perform 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. Follow taxonomies, benchmarks, and playbooks to keep testing consistent.
• Document reproducibly. Produce reports, datasets, and attack cases customers can act on.
• Work independently and asynchronously. Ensure flexible hours and meet deadlines.

Qualifications

Must-Have

• Fluent in English & Punjabi. Native fluency required.
• Strong judgment about language and content.
• Rigorous attention to detail. Notice subtle errors and inconsistencies.
• Structured approach. Consistently follow guidelines and quality standards.
• Effective communication skills. Explain reasoning clearly to technical and non-technical audiences.
• Adaptability. Thrive across projects, task types, and customers.

Preferred

• 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.

Resources & Support

• For details about the interview process and platform information, please check: https://talent.docs.mercor.com/welcome
• For any help or support, reach out to: [e-mail]