Ai Adversarial Specialist - Fully Remote | Upto $35/Hr

Mercor; San Francisco (CA); Hybride; GBP 25 000 - 36 000; Plein temps

Résumé du poste

Mercor is seeking AI Safety Experts to remotely assess and test AI models, focusing on jailbreaks, prompt injections, and bias exploitation. You will generate data, annotate vulnerabilities, and document actionable findings for customers, working independently across projects for a range of clients.

Ideal candidates have strong English and Thai language skills, experience in AI adversarial work or cybersecurity, and excellent communication to explain risks to both technical and non-technical

Qualifications

• Must-have fluency in English and Thai.
• Experience in AI adversarial red teaming, cybersecurity, or socio-technical probing.
• Strong communication skills to explain risks to both technical and non-technical stakeholders.
• Ability to move across projects and customers independently and asynchronously.

Responsabilités

• Red team conversational AI models and agents, focusing on jailbreaks, prompt injections, misuse cases, and bias exploitation.
• Generate high-quality human data, annotate failures, classify vulnerabilities, and flag systemic risks.
• Apply structure by following taxonomies, benchmarks, and playbooks for consistent testing.
• Document reproducibly by producing reports, datasets, and attack cases for customers.

Connaissances

English

Thai

Red team experience

AI adversarial work

Cybersecurity

Communication

Independent work

Description du poste

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 & Thai
Type: Contract
Compensation: $24–$35/hour
Location: Remote

Role Responsibilities

• Red team conversational AI models and agents. Focus on jailbreaks, prompt injections, misuse cases, and bias exploitation.


• Generate high-quality human data. Annotate failures, classify vulnerabilities, and flag systemic risks.


• Apply structure. Follow taxonomies, benchmarks, and playbooks to ensure consistent testing.


• Document reproducibly. Produce reports, datasets, and attack cases that customers can act on.


• Work independently and asynchronously. Participate in higher-sensitivity projects with clear guidelines and wellness resources.

Qualifications

Must-Have

• Fluent Language Skills Required: English & Thai


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


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


• Adaptability. Thrive on moving across projects and customers.

Preferred

• Experience in Adversarial ML, Cybersecurity, or socio-technical risk.


• Creative probing skills in psychology, acting, or writing for unconventional adversarial thinking.