Remote AI Safety Red Team Specialist

Mercor; Greater London; On-site; GBP 70,000 - 110,000; Full time

Job summary

Mercor is building a red team to probe AI models with adversarial inputs, surface vulnerabilities, and generate red team data that strengthens safety for customers.

This role reviews AI outputs touching sensitive topics, with topics clearly communicated beforehand; participation in high-sensitivity projects is optional and guided by wellbeing resources. You will perform red-teaming tasks, generate high-quality data, follow taxonomies, and produce reproducible reports.

Qualifications

• Prior red-team/AI adversarial work experience
• Ability to articulate risks to both technical and non-technical stakeholders
• Comfort using frameworks, benchmarks, and playbooks to guide testing

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 team experience

Curious/adversarial mindset

Structured/benchmark-driven

Effective communicator

Adaptable across projects

Job description

Mercor is building a red team to probe AI models with adversarial inputs, surface vulnerabilities, and generate red team data that strengthens safety for customers.

This role reviews AI outputs touching sensitive topics, with topics clearly communicated beforehand; participation in high-sensitivity projects is optional and guided by wellbeing resources. You will perform red-teaming tasks, generate high-quality data, follow taxonomies, and produce reproducible reports.