AI Red Team Specialist — Remote, English & Punjabi

Mercor; Karachi Division; On-site; PKR 24,986,000 - 33,315,000; Full time

Job summary

Mercor is assembling a red team to probe AI models with adversarial inputs, surface vulnerabilities, and generate data to improve safety. This work involves reviewing AI outputs that touch on sensitive topics such as bias, misinformation, or harmful content. Participation is optional and guided by clear guidelines and wellness resources.

You will document findings, produce reports and datasets, and help customers trust the safety of their AI by testing like an adversary.

Qualifications

• Experience in AI red teaming, cybersecurity, or socio-technical probing.
• Ability to annotate vulnerabilities and classify risks with frameworks.
• Familiarity with taxonomies, benchmarks, and playbooks for testing.
• Proven ability to communicate risks to technical and non-technical stakeholders.

Responsibilities

• Red team conversational AI models: jailbreaks, prompt injections, misuse cases, bias testing.
• 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 team experience

Adversarial thinking

Structured approach

Clear communication

Curiosity

Job description

Mercor is assembling a red team to probe AI models with adversarial inputs, surface vulnerabilities, and generate data to improve safety. This work involves reviewing AI outputs that touch on sensitive topics such as bias, misinformation, or harmful content. Participation is optional and guided by clear guidelines and wellness resources.

You will document findings, produce reports and datasets, and help customers trust the safety of their AI by testing like an adversary.