AI Safety Expert, English – Danish

This is a fully remote position, open to applicants in United States.

📋 Description

• Conduct red team assessments of conversational AI models and agents utilizing jailbreaks, prompt injections, misuse scenarios, bias exploitation, and multi-turn manipulations.

• Generate human data by annotating errors, classifying vulnerabilities, and identifying systemic risks.

• Implement taxonomies, benchmarks, and playbooks to ensure consistency in testing procedures.

• Create reproducible reports, datasets, and attack scenarios for clients.

• Test AI models with adversarial inputs to uncover vulnerabilities.

• Broaden evaluation coverage and detect vulnerabilities that automated tests may overlook.

• Assist clients in enhancing the safety, robustness, and trustworthiness of their AI systems.

⛳️ Requirements

• Native fluency in both English and Danish is essential.

• Previous experience in red teaming within AI adversarial contexts, cybersecurity, or socio-technical probing is required.

• Capability to push systems to their limits through adversarial testing.

• Familiarity with frameworks or benchmarks for structured testing processes.

• Proficient in communicating risks effectively to both technical and non-technical audiences.

• Flexibility to adapt across various projects and clients.

• Preferred qualifications include specializations in adversarial machine learning, cybersecurity, socio-technical risk, or creative probing.

• Candidates must not be H-1B or STEM OPT holders.

🏝️ Benefits

• Participation in higher-sensitivity projects is voluntary.

• Accessible guidelines and wellness resources are available prior to exposure to sensitive content.

• Fully remote work opportunities.

• Flexibility to work according to your own schedule.

• Weekly payments processed through Stripe or Wise.

• Competitive salary.

• Opportunities to collaborate with leading researchers in the field.

• Referral bonuses of up to $250 for each successful candidate referral.

• Reasonable accommodations available upon request.