AI Safety Experts – English, Norwegian

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

📋 Description

• Test red team conversational AI models and agents by employing jailbreaks, prompt injections, misuse scenarios, bias exploitation, and multi-turn manipulations.

• Document failures, categorize vulnerabilities, and identify systemic risks.

• Adhere to established taxonomies, benchmarks, and playbooks to maintain testing consistency.

• Generate reproducible reports, datasets, and attack scenarios.

• Examine AI systems for vulnerabilities overlooked by automated testing.

• Broaden evaluation coverage while minimizing production surprises.

• Enhance customer AI systems through human data-driven red teaming.

⛳️ Requirements

• Native proficiency in English and Norwegian.

• Previous experience in red teaming, including adversarial AI work, cybersecurity, or socio-technical probing.

• Capability to probe AI systems adversarially and push them to their limits.

• Familiarity with frameworks or benchmarks for structured testing.

• Proficiency in clearly communicating risks to both technical and non-technical stakeholders.

• Flexibility to adapt across different projects and clients.

• Must hold independent contractor status.

• H1-B and STEM OPT candidates are not eligible.

🏝️ Benefits

• Fully remote work environment.

• Flexible working hours / manage your own schedule.

• Weekly payments processed through Stripe or Wise.

• Project durations may be extended, reduced, or concluded early based on requirements and performance.

• Access to wellness resources for higher-sensitivity projects.

• Reasonable accommodations available upon request.

• Up to $250 referral bonus for each successful referral.