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

mercor; San Francisco (CA); Hybrid; CAD 39,000 - 43,000; Full time

Job summary

Mercor is seeking AI Safety Experts fluent in English and Urdu for a remote contract role. You will red team conversational AI models, identify vulnerabilities, and generate actionable reports.

You will work independently, document findings with reproducible data, and communicate risks to both technical and non-technical stakeholders.

Preferred candidates have adversarial ML experience and cybersecurity background, with creative probing skills.

Qualifications

• Native fluency in English and Urdu.
• 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.

Responsibilities

• Red team conversational AI models and agents. Conduct jailbreaks, prompt injections, misuse cases, and bias exploitation.
• Generate high-quality human data. Annotate failures, classify vulnerabilities, and flag systemic risks.
• Apply structure using taxonomies, benchmarks, and playbooks to maintain testing consistency.
• Document reproducibly. Produce reports, datasets, and attack cases that customers can act on.
• Work independently and asynchronously to meet deadlines while improving AI model performance.

Skills

Red teaming

English Urdu fluency

Cybersecurity experience

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

Role Responsibilities

• Red team conversational AI models and agents. Conduct jailbreaks, prompt injections, misuse cases, and bias exploitation.
• Generate high-quality human data. Annotate failures, classify vulnerabilities, and flag systemic risks.
• Apply structure using taxonomies, benchmarks, and playbooks to maintain testing consistency.
• Document reproducibly. Produce reports, datasets, and attack cases that customers can act on.
• Work independently and asynchronously to meet deadlines while improving AI model performance.

Qualifications

Must-Have

• Native fluency in English and Urdu.
• 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 : jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction.
• Background in Cybersecurity : penetration testing, exploit development, reverse engineering.
• Expertise in socio-technical risk: harassment/disinfo probing, abuse analysis, conversational AI testing.
• Creative probing skills in psychology, acting, or writing for unconventional adversarial thinking.