Remote AI Red Team Analyst - Safety Expert

Mercor; Greater London; Remote; GBP 40,000 - 70,000; Full time

Job summary

Mercor is building a remote AI safety red team in the UK to probe conversational models with adversarial inputs. You will annotate failures, classify vulnerabilities, and generate high-quality data to help strengthen AI systems.

You’ll follow taxonomies and playbooks to keep testing consistent, document reproducibly, and communicate findings to technical and non-technical audiences while working across projects.

Qualifications

• Strong judgment about language and content: assess AI outputs for accuracy, completeness and safety.
• Rigorous: notice subtle errors, inconsistencies, and gaps that others miss.
• Structured: follow guidelines and quality standards across tasks.
• Clear reasoning: explain decisions to both technical and non-technical audiences.
• Adaptable: handle multiple projects and customer contexts.

Responsibilities

• Red-team conversational AI models: jailbreaks, prompt injections, misuse cases, bias exploitation.
• 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

Adversarial reasoning

Attention to detail

Structured thinking

Clear communication

Adaptability

Job description

Mercor is building a remote AI safety red team in the UK to probe conversational models with adversarial inputs. You will annotate failures, classify vulnerabilities, and generate high-quality data to help strengthen AI systems.

You’ll follow taxonomies and playbooks to keep testing consistent, document reproducibly, and communicate findings to technical and non-technical audiences while working across projects.