Remote AI Safety Red Team Specialist

Mercor; Karachi Division; Remote; PKR 24,993,000 - 36,101,000; Full time

Job summary

Mercor is building a red team for AI safety, focusing on adversarial testing of conversational models. This remote role invites you to probe models with jailbreaks, prompt injections, and bias exploration across multiple projects.

You will generate high-quality data, annotate failures, and document findings with clear reports and reproducible datasets to help customers strengthen their AI systems. Remote and flexible collaboration offered.

Qualifications

• Prior red teaming experience in AI adversarial work
• Curious and adversarial: push systems to breaking points
• Structured: use frameworks or benchmarks
• Communicative: explain risks to technical and non-technical stakeholders
• Adaptable: move across projects and customers

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

Adversarial thinking

Structured framework

Communicative

Adaptable

Job description

Mercor is building a red team for AI safety, focusing on adversarial testing of conversational models. This remote role invites you to probe models with jailbreaks, prompt injections, and bias exploration across multiple projects.

You will generate high-quality data, annotate failures, and document findings with clear reports and reproducible datasets to help customers strengthen their AI systems. Remote and flexible collaboration offered.