AI Safety Specialist - Fully Remote | Upto $45/hr

mercor; San Francisco (CA); Hybrid; AUD 57,000 - 89,000; Full time

Job summary

Mercor seeks AI Safety Experts to rigorously test and improve conversational AI systems in a global, remote contract role.

Qualified candidates are native in English and Portuguese and have red teaming experience in AI adversarial work or cybersecurity. Strong communication skills to explain risks to both technical and non-technical stakeholders are essential.

Qualifications

• Native fluency in English.
• Native fluency in Portuguese (global, excluding Brazilian Portuguese).
• Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing.
• Strong communication skills to explain risks clearly to technical and non-technical stakeholders.

Responsibilities

• Red team conversational AI models and agents by performing jailbreaks, prompt injections, misuse cases, and bias exploitation.
• 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 by producing reports, datasets, and attack cases that customers can act on.
• Work independently and asynchronously to improve AI model performance and ensure safety.

Skills

English

Portuguese

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 & Portuguese (global) Type: Contract Compensation: $29–$45/hour Location: Remote

Responsibilities

• Red team conversational AI models and agents by performing jailbreaks, prompt injections, misuse cases, and bias exploitation.
• 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 by producing reports, datasets, and attack cases that customers can act on.
• Work independently and asynchronously to improve AI model performance and ensure safety.

Qualifications

Must-Have

• Native fluency in English and Portuguese (global, excluding Brazilian Portuguese).
• Prior red teaming experience in AI adversarial work , cybersecurity , or socio-technical probing .
• Strong communication skills to explain risks clearly to technical and non-technical stakeholders.

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 skills: psychology, acting, writing for unconventional adversarial thinking.

Originally posted on Himalayas