Remote AI Adversarial Specialist

Mercor; Helsinki; Remote; EUR 78,000 - 104,000; Full time

Job summary

Mercor is building a remote red team to proactively test AI systems by probing models with adversarial prompts, bias checks, and risk scenarios. This project focuses on reviewing outputs touching sensitive topics, with clear guidelines and wellness resources, and participation is supported throughout the process.

You will document reproducible findings, annotate vulnerabilities, and provide attack cases that customers can act on.

Qualifications

• Red teaming experience in AI adversarial work or cybersecurity.
• Curious and adversarial: you instinctively push systems to breaking points.
• Structured: you use frameworks or benchmarks, not just random hacks.
• Communicative: you explain risks clearly to technical and non-technical stakeholders.
• 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

Skills

Red teaming

Adversarial mindset

Structured thinking

Excellent communication

Adaptability

Tools

Taxonomies

Benchmarks

Playbooks

Job description

Mercor is building a remote red team to proactively test AI systems by probing models with adversarial prompts, bias checks, and risk scenarios. This project focuses on reviewing outputs touching sensitive topics, with clear guidelines and wellness resources, and participation is supported throughout the process.

You will document reproducible findings, annotate vulnerabilities, and provide attack cases that customers can act on.