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

mercor; Pakistan; Remoto; PKR 7.628.000 - 8.391.000; Part-time

Descrizione del lavoro

Mercor is seeking AI Safety Experts to test and break AI systems remotely. You will perform red team assessments on conversational models, document findings, and produce actionable reports for customers.

Requires native fluency in English and Urdu, prior adversarial AI/red-teaming experience, and strong communication to explain risks to technical and non‑technical stakeholders. The role emphasizes independence and asynchronous work to meet deadlines.

Competenze

• Native fluency in English and Urdu.
• Experience in red teaming AI adversarial work, cybersecurity, or socio-technical probing.
• Ability to explain risks to both technical and non-technical stakeholders.

Mansioni

• Red team conversational AI models and agents, including jailbreaks and prompt injections.
• Generate high-quality human data; annotate failures and flag systemic risks.
• Apply structured taxonomies and playbooks to maintain testing consistency.
• Document reproducibly with reports, datasets, and attack cases for customers.
• Work independently and asynchronously to meet deadlines while improving model performance.

Conoscenze

Bilingual English/Urdu

Red teaming / adversarial AI

Strong communication

Descrizione del lavoro

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.