Remote AI Adversarial Red Team Engineer

Obsidian; Greater London; Remote; GBP 65,000 - 100,000; Full time

Job summary

Mercor is assembling a remote red team to probe AI models with adversarial inputs, surface vulnerabilities, and generate data that strengthens customer AI systems. The work is text-based and designed to be safety-focused with clear guidelines and wellness resources.

You will review AI outputs touching on sensitive topics like bias or misinformation, annotate and classify findings, and document reproducible artifacts for customers to act on.

Qualifications

• You bring prior red teaming experience (AI adversarial work, cybersecurity, socio-technical probing)
• You’re curious and adversarial: you instinctively push systems to breaking points
• You’re structured: you use frameworks or benchmarks, not just random hacks
• You’re communicative: you explain risks clearly to technical and non-technical stakeholders
• You’re adaptable: thrive on 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

Job description

Mercor is assembling a remote red team to probe AI models with adversarial inputs, surface vulnerabilities, and generate data that strengthens customer AI systems. The work is text-based and designed to be safety-focused with clear guidelines and wellness resources.

You will review AI outputs touching on sensitive topics like bias or misinformation, annotate and classify findings, and document reproducible artifacts for customers to act on.