Remote AI Safety Red Team Specialist

Mercor; Toronto; On-site; CAD 90,000 - 130,000; Full time

Job summary

Mercor is assembling a remote AI red team to proactively probe AI models with adversarial inputs, assess vulnerabilities, and generate actionable data for safer customer AI systems.

You will work on high-sensitivity topics with clear guidelines and wellness resources; participation in certain projects is optional. Strong English and Swedish language requirements apply, with a focus on rigorous, structured testing and reproducible results.

Qualifications

• Prior red teaming experience (AI adversarial work, cybersecurity, socio-technical probing).
• Curious and adversarial: you instinctively push systems to breaking points.
• Structured: you use frameworks or benchmarks, not just random hacks.
• Communicative: you clearly explain risks to technical and non-technical stakeholders.
• Adaptable: you thrive moving 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 team experience

Adversarial mindset

Structured approach

Excellent communication

Adaptable

Job description

Mercor is assembling a remote AI red team to proactively probe AI models with adversarial inputs, assess vulnerabilities, and generate actionable data for safer customer AI systems.

You will work on high-sensitivity topics with clear guidelines and wellness resources; participation in certain projects is optional. Strong English and Swedish language requirements apply, with a focus on rigorous, structured testing and reproducible results.