Remote AI Safety Red Team Specialist

Obsidian; Quezon City; On-site; PHP 5,478,000 - 9,130,000; Full time

Job summary

Mercor is building a specialized AI safety red team to probe conversational models with adversarial inputs, jailbreak attempts, and misuse scenarios. Native fluency in English and Vietnamese is required, and remote collaboration across projects and clients is expected.

You will generate high-quality data, apply structured testing frameworks, and document reproducible artifacts to help customers strengthen their AI systems against emerging risks.

Qualifications

• Experience conducting red-team tasks on AI systems.
• Ability to design adversarial tests and document findings clearly.
• Familiarity with risk assessment and safety benchmarks.

Responsibilities

• Red team conversational AI models and agents: jailbreaks, prompt injections, misuse cases, bias exploitation, multi-turn manipulation
• Generate high-quality human data: annotate failures, classify vulnerabilities, and flag systemic risks
• Apply structure: follow taxonomies, benchmarks, and playbooks to keep testing consistent
• Document reproducibly: produce reports, datasets, and attack cases customers can act on

Skills

Red teaming

AI adversarial testing

Prompt injection

Bias analysis

Cybersecurity basics

Structured testing

Clear communication

Job description

Mercor is building a specialized AI safety red team to probe conversational models with adversarial inputs, jailbreak attempts, and misuse scenarios. Native fluency in English and Vietnamese is required, and remote collaboration across projects and clients is expected.

You will generate high-quality data, apply structured testing frameworks, and document reproducible artifacts to help customers strengthen their AI systems against emerging risks.