Remote AI Adversarial Red Team Specialist (EN/FI)

Obsidian; Helsinki; Remote; EUR 78,000 - 113,000; Full time

Job summary

Mercor is assembling a remote red team to probe AI models with adversarial inputs, surface vulnerabilities, and generate data that enhances safety for customers. The role involves risk assessment of outputs touching sensitive topics such as bias and misinformation, with clear guidelines and wellness resources in place.

You will contribute to testing frameworks, produce reproducible reports, and collaborate with stakeholders across projects to strengthen AI safety and reliability.

Qualifications

• Red team experience in AI adversarial work, cybersecurity, socio-technical probing.
• Curious and adversarial mindset, pushing systems to breaking points.
• Structured approach using frameworks or benchmarks.
• Strong communication of risks to both technical and non-technical stakeholders.
• Flexible, able to 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 experience

Curious and adversarial

Structured

Communicative

Adaptable

Job description

Mercor is assembling a remote red team to probe AI models with adversarial inputs, surface vulnerabilities, and generate data that enhances safety for customers. The role involves risk assessment of outputs touching sensitive topics such as bias and misinformation, with clear guidelines and wellness resources in place.

You will contribute to testing frameworks, produce reproducible reports, and collaborate with stakeholders across projects to strengthen AI safety and reliability.