AI Safety Expert – English, Norwegian

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

📋 Description

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

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

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

• Generate reproducible reports, datasets, and attack scenarios.

• Detect vulnerabilities that automated testing may overlook.

• Enhance evaluation coverage and minimize unexpected issues in production.

• Fortify customer AI systems through data-driven red teaming efforts.

⛳️ Requirements

• Native or fluent proficiency in both English and Norwegian.

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

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

• Familiarity with frameworks or benchmarks for structured testing methodologies.

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

• Flexibility to adapt across various projects and client needs.

• Must operate as an independent contractor.

• Not eligible if holding an H1-B or STEM OPT status.

• Preferred expertise includes adversarial machine learning, cybersecurity, socio-technical risk, or innovative probing techniques.

🏝️ Benefits

• Fully remote position.

• Flexible working hours; tasks can be completed according to your own schedule.

• Weekly compensation through Stripe or Wise.

• Option to engage in higher-sensitivity projects.

• Access to clear content guidelines and wellness resources.

• Opportunity to gain experience in human data-driven AI red teaming.

• Direct involvement in enhancing the robustness, safety, and trustworthiness of AI systems.

• Collaboration opportunities with top researchers in the field.

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