AI Safety Expert - Red Teaming

mercor; United States; Remote; USD 28,000 - 30,000; Part time

Job summary

Mercor is seeking AI Safety Experts to join our remote contract team. This role focuses on evaluating and improving the safety of AI systems in English and Odia, with flexible, remote work.

You will red-team conversational models, annotate failures, and document findings to help partners reduce risky behavior and system vulnerabilities. Strong communication is essential for stakeholder engagement.

Qualifications

• Fluent English and Odia required.
• Red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing.
• Strong communication skills to explain risks to diverse stakeholders.

Responsibilities

• Red team conversational AI models and agents to identify jailbreaks, prompt injections, and misuse cases.
• Generate high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks.
• Apply structure by following taxonomies, benchmarks, and playbooks to maintain consistent testing.
• Document reproducibly to produce reports, datasets, and attack cases for customer action.
• Work independently and asynchronously to meet deadlines while improving AI model performance.

Skills

English

Odia

Red team experience

Communication skills

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 & Odia
Type: Contract
Compensation: $20–$22/hour
Location: Remote

Responsibilities

• Red team conversational AI models and agents to identify jailbreaks, prompt injections, and misuse cases.
• Generate high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks.
• Apply structure by following taxonomies, benchmarks, and playbooks to maintain consistent testing.
• Document reproducibly to produce reports, datasets, and attack cases for customer action.
• Work independently and asynchronously to meet deadlines while improving AI model performance .

Qualifications

Must-Have

• Fluent Language Skills Required: English & Odia.
• 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 , Cybersecurity , or Socio-technical risk .
• Skills in Creative probing such as psychology, acting, or writing for unconventional adversarial thinking.