AI Safety Expert - Bilingual

mercor; United States; Remoto; USD 23.000 - 34.000; Tempo pieno

Descrizione del lavoro

Mercor is seeking AI Safety Experts fluent in English and Indonesian for a remote contract role. You will red-team AI systems, test jailbreaks and prompt injections, and document cases to drive safer deployments.

You will explain risks clearly to both technical and non-technical teammates, contributing to risk assessments and playbooks across Mercor's AI projects with researchers and engineers worldwide.

Competenze

• Must have fluency in English and Indonesian.
• Prior red teaming experience in AI adversarial work, cybersecurity, or socio-technical probing.
• Ability to explain risks clearly to technical and non-technical stakeholders.

Mansioni

• 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 using taxonomies, benchmarks, and playbooks to maintain consistent testing.
• Document reproducibly. Produce reports, datasets, and attack cases that customers can act on.

Conoscenze

Fluent in English

Fluent in Indonesian

Red teaming experience

Explain risks to stakeholders

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 & Indonesian

Type

Contract

Compensation

$17–$25/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 using taxonomies, benchmarks, and playbooks to maintain consistent testing.
• Document reproducibly. Produce reports, datasets, and attack cases that customers can act on.

Qualifications

• Must-Have
  • Fluent in English and Indonesian .
  • Prior red teaming experience in AI adversarial work , cybersecurity , or socio-technical probing.
  • Ability to explain risks clearly 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.
  • Knowledge of socio-technical risk: harassment/disinfo probing, abuse analysis, conversational AI testing.