AI Safety Expert - Red Teaming

mercor; India; Remote; INR 2,670,000 - 2,937,000; Full time

Job summary

Mercor invites applications for AI Safety Experts specializing in English and Odia for a remote contract role. You will assess and strengthen AI systems through red-teaming, data annotation, and vulnerability classification to drive safer deployments.

The job pays $20–$22 per hour and requires fluent English and Odia, prior adversarial AI or cybersecurity experience, and the ability to explain risks clearly to technical and non-technical audiences.

Qualifications

• Fluent in English and Odia.
• 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 to identify jailbreaks, prompt injections, and misuse cases.
• Annotate failures and classify vulnerabilities to generate high-quality data and flag systemic risks.
• Follow 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 fluency

Adversarial AI experience

Strong communication

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.