AI Safety Specialist - Fully Remote | Upto $22/hr

Mercor; Greater London; Remote; GBP 21,000 - 23,000; Full time

Job summary

Mercor is seeking AI Safety Experts for remote, contract work focused on auditing and red-teaming conversational AI models. You will test jailbreaks, prompt injections, and misuse scenarios, producing high-quality data and reproducible reports for customers.

You must be fluent in English and Assamese, with prior red-teaming, AI adversarial work, or cybersecurity experience. Strong communication is essential to explain risks to technical and non-technical stakeholders.

Qualifications

• Must be fluent in English and Assamese.
• Prior red team experience in AI adversarial work or cybersecurity.
• Strong communication to explain risks to technical and non-technical stakeholders.

Responsibilities

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

Skills

Fluent in English

Fluent in Assamese

Red teaming experience

Cybersecurity

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 & Assamese

Type: Contract

Compensation: $20–$22/hour

Location: Remote

Role Responsibilities

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

Qualifications

Must-Have

• Fluent in English and Assamese.
• Prior experience in red teaming, AI adversarial work, or cybersecurity.
• Strong communication skills to explain risks to both technical and non-technical stakeholders.

Preferred

• Experience with adversarial ML, cybersecurity, and socio-technical risk analysis.
• Skills in creative probing such as psychology, acting, or unconventional adversarial thinking.