AI Safety Specialist - Fully Remote

Mercor; Berlin; Remote; EUR 70.000 - 110.000; Vollzeit

Zusammenfassung

Mercor is building a red team for AI safety, focusing on adversarial testing of conversational models. You’ll explore jailbreaks, prompt injections, and misuse scenarios while generating high-quality data and reproducible artifacts to reinforce client AI systems.

This remote role offers flexible engagement across projects and clients, with clear guidelines and wellness resources for sensitive content. English and Dutch fluency are required.

Qualifikationen

• 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.

Aufgaben

• 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.

Kenntnisse

Red team testing

Adversarial AI

Prompt injection

Bias exploitation

Multi-turn manipulation

Tools

Taxonomies

Benchmarks

Playbooks

Jobbeschreibung

Location

Remote

Fluent Language Skills Required

English & Dutch. Native fluency in English and Dutch is required for this position.

Why This Role Exists

At Mercor, we believe the safest AI is the one that’s already been attacked — by us. We are assembling a red team for this project - human data experts who probe AI models with adversarial inputs, surface vulnerabilities, and generate the red team data that makes AI safer for our customers.

This project involves reviewing AI outputs that touch on sensitive topics such as bias, misinformation, or harmful behaviors. All work is text-based, and participation in higher-sensitivity projects is optional and supported by clear guidelines and wellness resources. Before being exposed to any content, the topics will be clearly communicated.

What You’ll Do

• 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

Who You Are

• 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

Nice-to-Have Specialties

• Adversarial ML: jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction
• Cybersecurity: penetration testing, exploit development, reverse engineering
• Socio-technical risk: harassment/disinfo probing, abuse analysis, conversational AI testing
• Creative probing: psychology, acting, writing for unconventional adversarial thinking

What Success Looks Like

• You uncover vulnerabilities automated tests miss
• You deliver reproducible artifacts that strengthen customer AI systemsEvaluation coverage expands: more scenarios tested, fewer surprises in production
• Mercor customers trust the safety of their AI because you’ve already probed it like an adversary

Why Join Mercor

• Build experience in human data-driven AI red teaming at the frontier of safety
• Play a direct role in making AI systems more robust, safe, and trustworthy