Remote Adversarial ML Specialist

Mercor; Stockholms kommun; Remote; SEK 900,000 - 1,200,000; Full time

Job summary

Mercor is assembling a red team to probe AI models with adversarial inputs, surface vulnerabilities, and generate red team data for safer AI systems. This is a remote role requiring fluency in English and Swedish, with topics clearly communicated before exposure.

You will annotate failures, classify vulnerabilities, and document reproducible attack cases, following established taxonomies and playbooks to ensure consistency across projects.

Qualifications

• Prior red teaming experience (AI adversarial work, cybersecurity, socio-technical probing).
• Structured: you use frameworks or benchmarks, not just random hacks.
• You're curious and adversarial: you push systems to breaking points.
• You're communicative: you 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

Adversarial ML

Cybersecurity

Socio-technical risk

Creative probing

English & Swedish proficiency

Job description

Mercor is assembling a red team to probe AI models with adversarial inputs, surface vulnerabilities, and generate red team data for safer AI systems. This is a remote role requiring fluency in English and Swedish, with topics clearly communicated before exposure.

You will annotate failures, classify vulnerabilities, and document reproducible attack cases, following established taxonomies and playbooks to ensure consistency across projects.