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

mercor; Pakistan; Remote; PKR 7,628,000 - 8,391,000; Part time

Job summary

Mercor is hiring AI Safety Experts to test and harden conversational AI with English and Punjabi contexts in a remote, contract-based role. You will contribute to adversarial evaluation, data collection, and risk assessment across multiple projects and customers.

The position emphasizes clear communication of risks to both technical and non-technical stakeholders, plus flexibility to move across different clients and engagements.

Qualifications

• Fluent in English and Punjabi.
• Prior experience in red teaming (AI adversarial work, cybersecurity, socio-technical probing).
• Strong communication skills. Explain risks clearly to technical and non-technical stakeholders.
• Adaptable. Thrive on moving across projects and customers.

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 consistent testing.
• Document reproducibly. Produce reports, datasets, and attack cases for customer action.

Skills

English & Punjabi Fluency

Red Teaming Experience

Communication Skills

Adaptability

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 .

Role

Position: AI Safety Experts — English & Punjabi
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 consistent testing.


• Document reproducibly. Produce reports, datasets, and attack cases for customer action.

Qualifications Must-Have

• Fluent in English and Punjabi.


• Prior experience in red teaming (AI adversarial work, cybersecurity, socio-technical probing).


• Strong communication skills. Explain risks clearly to technical and non-technical stakeholders.


• Adaptable. Thrive on moving across projects and customers.

Preferred

• Experience in Adversarial ML : jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction.


• Cybersecurity skills: penetration testing, exploit development, reverse engineering.


• Socio-technical risk expertise: harassment/disinfo probing, abuse analysis, conversational AI testing.


• Creative probing abilities: psychology, acting, writing for unconventional adversarial thinking.

Originally posted on Himalayas