AI Safety Expert for English and Danish Red Teaming

Lead adversarial testing of conversational AI in English and Danish, probing models and agents to surface vulnerabilities related to bias, misinformation, and harmful behaviors. This text-based role produces reproducible attack cases, datasets, and reports that help customers harden their systems. Higher-sensitivity content is optional and accompanied by clear guidelines and wellness resources, and topics will be disclosed before exposure.

• Red team conversational AI models and agents, including jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation.
• Review AI outputs that touch on sensitive topics such as bias, misinformation, or harmful behaviors.
• Generate high-quality human data: annotate failures, classify vulnerabilities, and flag systemic risks.
• Follow taxonomies, benchmarks, and playbooks to keep testing consistent and structured.
• Document reproducibly: produce reports, datasets, and attack cases customers can act on.

• Prior red teaming experience, such as AI adversarial work, cybersecurity, or socio-technical probing.
• Native fluency in English and Danish is required.
• Curious and adversarial mindset, with an instinct to push systems to breaking points.
• Structured approach, using frameworks or benchmarks rather than random testing.
• Strong communication skills, able to explain risks to technical and non-technical stakeholders.
• Adaptable, comfortable moving across projects and customers.

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

• Uncovering vulnerabilities that automated tests miss.
• Delivering reproducible artifacts that strengthen customer AI systems.
• Expanding evaluation coverage so more scenarios are tested and fewer surprises occur in production.
• Increasing customer trust in the safety and robustness of their AI because it has been probed like an adversary.

• Location: Remote.
• Employment type: hourly engagement.
• All tasks are text-based.
• Participation in higher-sensitivity projects is optional, and such projects are supported by guidelines and wellness resources; topics are communicated in advance.

• Pay rate: 48 - 62 hourly.

• Native fluency in English and Danish is required for this position.