Remote AI Safety Red Team Specialist

Mercor; Singapore; Remote; SGD 90,000 - 130,000; Full time

Job summary

Mercor in Singapore is seeking a remote red team specialist to probe AI models with adversarial inputs. You will simulate jailbreaks, prompt injections, and misuse cases to surface vulnerabilities before deployment.

You’ll annotate failures, classify risks, and produce reproducible reports and datasets that help customers strengthen their AI safety. Strong communication and a disciplined, framework-driven approach are essential.

Qualifications

• Prior red teaming experience in AI adversarial work or cybersecurity.
• Curious and adversarial mindset with a drive to push systems.
• Structured approach using frameworks or benchmarks.
• Able to clearly communicate risks to technical and non-technical audiences.
• Flexible and capable of moving across projects and customers.

Responsibilities

• Red team conversational AI models: jailbreaks, prompt injections, misuse cases.
• Generate high-quality human data: annotate failures and classify risks.
• Apply structure: follow taxonomies, benchmarks, and playbooks for testing.
• Document reproducibly: produce reports, datasets, and attack cases for customers.

Skills

Red team adversarial testing

Cybersecurity testing

Structured testing frameworks

Communication to stakeholders

Adaptability across projects

Education

Relevant CS/Engineering degree

Tools

Adversarial ML tools

Cybersecurity tools

Risk/assessment frameworks

RLHF/DPO attack concepts

Job description

Mercor in Singapore is seeking a remote red team specialist to probe AI models with adversarial inputs. You will simulate jailbreaks, prompt injections, and misuse cases to surface vulnerabilities before deployment.

You’ll annotate failures, classify risks, and produce reproducible reports and datasets that help customers strengthen their AI safety. Strong communication and a disciplined, framework-driven approach are essential.