Remote AI Safety Red Team Expert

Mercor; Helsinki; On-site; EUR 85,000 - 120,000; Full time

Benefits offered by this job

Remote-friendly operations

Wellness resources and guidelines

Job summary

Mercor is assembling a remote AI red team focused on reviewing outputs that touch on sensitive topics. You’ll simulate adversarial scenarios, annotate failures, and generate data to surface vulnerabilities while adhering to clear guidelines.

The role emphasizes English and Finnish communication and is suitable for someone comfortable working across projects and customers. The team aims to strengthen safety for Mercor’s AI products, with work shared across multiple clients and contexts.

Qualifications

• Experience in red team AI adversarial work or cybersecurity.
• Ability to push systems to breaking points using structured methods.
• Familiarity with frameworks, benchmarks, and playbooks for testing consistency.
• Ability to explain risks clearly to technical and non-technical stakeholders.

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

Adversarial thinking

Structured testing

Clear communicator

Adaptable to projects

Job description

Mercor is assembling a remote AI red team focused on reviewing outputs that touch on sensitive topics. You’ll simulate adversarial scenarios, annotate failures, and generate data to surface vulnerabilities while adhering to clear guidelines.

The role emphasizes English and Finnish communication and is suitable for someone comfortable working across projects and customers. The team aims to strengthen safety for Mercor’s AI products, with work shared across multiple clients and contexts.